[{"slug": "claude-5-opus-high", "name": "Claude 5 Opus (high)", "vendor": "Anthropic", "model_family": "claude-5-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 5 Opus (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 100.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-5-opus", "name": "Claude 4.5 Opus", "vendor": "Anthropic", "model_family": "claude-4-5-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.5 Opus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 15, "best_success_rate": 96.25, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "fable-5", "name": "Fable 5", "vendor": "Anthropic", "model_family": "fable-5", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Fable 5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 8, "best_success_rate": 95.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-5", "name": "GPT-5.5", "vendor": "openai", "model_family": "gpt-5-5", "parameter_count_b": null, "context_length": 1050000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5.5", "card_summary": "openai GPT-5.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 10, "best_success_rate": 93.25, "input_price_per_million": 5.0, "output_price_per_million": 30.0}, {"slug": "claude-4-7-opus", "name": "Claude 4.7 Opus", "vendor": "Anthropic", "model_family": "claude-4-7-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.7 Opus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 10, "best_success_rate": 93.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-sonnet", "name": "Claude 4 Sonnet", "vendor": "Anthropic", "model_family": "claude-4-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4 Sonnet \u2014 balanced frontier model for coding agents.", "is_rl_checkpoint": false, "score_count": 20, "best_success_rate": 92.75, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-5-sonnet-20241022", "name": "Claude 3.5 Sonnet (2024-10-22)", "vendor": "Anthropic", "model_family": "claude-3-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.5 Sonnet (2024-10-22) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 20, "best_success_rate": 92.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-3-7-flash-high", "name": "Gemini 3.7 Flash (high)", "vendor": "Google", "model_family": "gemini-3-7-flash", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3.7 Flash (high tier) for fast agentic coding runs.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 91.01, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-3-5-flash", "name": "Gemini 3.5 Flash", "vendor": "google", "model_family": "gemini-3-5-flash", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemini-3.5-flash", "card_summary": "google Gemini 3.5 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 8, "best_success_rate": 90.25, "input_price_per_million": 1.5, "output_price_per_million": 9.0}, {"slug": "o1", "name": "o1", "vendor": "openai", "model_family": "o1", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/o1", "card_summary": "openai o1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 90.25, "input_price_per_million": 15.0, "output_price_per_million": 60.0}, {"slug": "gemini-3-1-pro", "name": "Gemini 3.1 Pro", "vendor": "Google", "model_family": "gemini-3-1-pro", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3.1 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 10, "best_success_rate": 90.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-5-opus-xhigh", "name": "Claude 5 Opus (xhigh)", "vendor": "Anthropic", "model_family": "claude-5-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 5 Opus (xhigh) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 89.14, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-5-haiku", "name": "Claude 3.5 Haiku", "vendor": "Anthropic", "model_family": "claude-3-5-haiku", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.5 Haiku on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 89.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-2", "name": "GPT-5.2", "vendor": "openai", "model_family": "gpt-5-2", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5.2", "card_summary": "openai GPT-5.2 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 10, "best_success_rate": 89.0, "input_price_per_million": 1.75, "output_price_per_million": 14.0}, {"slug": "claude-5-opus-max", "name": "Claude 5 Opus (max)", "vendor": "Anthropic", "model_family": "claude-5-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 5 Opus (max) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 88.76, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-2-medium", "name": "GPT-5.2 (medium)", "vendor": "OpenAI", "model_family": "gpt-5-2", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.2 (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 88.75, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-2-5-pro", "name": "Gemini 2.5 Pro", "vendor": "google", "model_family": "gemini-2-5-pro", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemini-2.5-pro", "card_summary": "google Gemini 2.5 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 9, "best_success_rate": 88.5, "input_price_per_million": 1.25, "output_price_per_million": 10.0}, {"slug": "gpt-5-high", "name": "GPT-5 (high)", "vendor": "OpenAI", "model_family": "gpt-5", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 88.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k3", "name": "KIMI K3", "vendor": "Moonshot", "model_family": "kimi-k3", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k3", "card_summary": "Moonshot KIMI K3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 87.64, "input_price_per_million": 3.0, "output_price_per_million": 15.0}, {"slug": "gpt-4", "name": "GPT-4", "vendor": "openai", "model_family": "gpt-4", "parameter_count_b": null, "context_length": 8191, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-4", "card_summary": "openai GPT-4 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 19, "best_success_rate": 87.5, "input_price_per_million": 30.0, "output_price_per_million": 60.0}, {"slug": "o4-mini-high", "name": "o4 mini (high)", "vendor": "openai", "model_family": "o4", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/o4-mini-high", "card_summary": "openai o4 mini (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 87.3, "input_price_per_million": 1.1, "output_price_per_million": 4.4}, {"slug": "claude-4-5-sonnet", "name": "Claude 4.5 Sonnet", "vendor": "Anthropic", "model_family": "claude-4-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.5 Sonnet on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 21, "best_success_rate": 87.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-2-xhigh", "name": "GPT-5.2 (xhigh)", "vendor": "OpenAI", "model_family": "gpt-5-2", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.2 (xhigh) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 86.75, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-medium", "name": "GPT-5 (medium)", "vendor": "OpenAI", "model_family": "gpt-5", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5 (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 17, "best_success_rate": 86.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "fable-5-max-with-fallback", "name": "Fable 5 Max With Fallback", "vendor": "Fable", "model_family": "fable-5-max-with-fallback", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Fable 5 (max) coding model with fallback routing on benchmarks.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 86.52, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-2-5-flash", "name": "Gemini 2.5 Flash", "vendor": "google", "model_family": "gemini-2-5-flash", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemini-2.5-flash", "card_summary": "google Gemini 2.5 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 85.5, "input_price_per_million": 0.3, "output_price_per_million": 2.5}, {"slug": "gemini-3-0-pro", "name": "Gemini 3.0 Pro", "vendor": "Google", "model_family": "gemini-3-0-pro", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3.0 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 85.5, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-5-opus-medium", "name": "Claude 5 Opus (medium)", "vendor": "Anthropic", "model_family": "claude-5-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 5 Opus (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 85.02, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o3-pro-high", "name": "o3 pro (high)", "vendor": "OpenAI", "model_family": "o3", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI o3 pro (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 84.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4o-mini", "name": "GPT-4o mini", "vendor": "openai", "model_family": "gpt-4o-mini", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-4o-mini", "card_summary": "openai GPT-4o mini on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 84.75, "input_price_per_million": 0.15, "output_price_per_million": 0.6}, {"slug": "o3-high", "name": "o3 (high)", "vendor": "OpenAI", "model_family": "o3", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI o3 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 84.74, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o4-mini", "name": "o4 mini", "vendor": "openai", "model_family": "o4", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/o4-mini", "card_summary": "openai o4 mini on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 23, "best_success_rate": 84.45, "input_price_per_million": 1.1, "output_price_per_million": 4.4}, {"slug": "deepseek-r1-0528", "name": "DeepSeek R1 0528", "vendor": "deepseek", "model_family": "deepseek-r1-0528", "parameter_count_b": null, "context_length": 163840, "homepage_url": null, "hf_model_id": null, "openrouter_id": "deepseek/deepseek-r1-0528", "card_summary": "deepseek DeepSeek R1 0528 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 84.36, "input_price_per_million": 0.5, "output_price_per_million": 2.1500000000000004}, {"slug": "claude-4-8-opus", "name": "Claude 4.8 Opus", "vendor": "Anthropic", "model_family": "claude-4-8-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.8 Opus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 7, "best_success_rate": 84.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-4-5-high", "name": "GROK 4.5 (high)", "vendor": "xAI", "model_family": "grok-4-5-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 4.5 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 84.27, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "fable-5-[high]", "name": "Fable 5 [high]", "vendor": "Anthropic", "model_family": "fable-5-[high]", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Fable 5 [high] on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 84.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-8-opus-max", "name": "Claude 4.8 Opus (max)", "vendor": "Anthropic", "model_family": "claude-4-8-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.8 Opus (max) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 83.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-8-max", "name": "Qwen3.8 Max", "vendor": "Qwen", "model_family": "qwen3-8-max", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3.8-max", "card_summary": "Qwen Qwen3.8 Max on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 83.9, "input_price_per_million": 2.0, "output_price_per_million": 6.0}, {"slug": "claude-4-8-opus-xhigh", "name": "Claude 4.8 Opus (xhigh)", "vendor": "Anthropic", "model_family": "claude-4-8-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.8 Opus (xhigh) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 83.15, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-2-5-pro-preview", "name": "Gemini 2.5 Pro Preview", "vendor": "google", "model_family": "gemini-2-5-pro-preview", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemini-2.5-pro-preview", "card_summary": "google Gemini 2.5 Pro Preview on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 83.1, "input_price_per_million": 1.25, "output_price_per_million": 10.0}, {"slug": "gpt-5-5-xhigh", "name": "GPT-5.5 (xhigh)", "vendor": "OpenAI", "model_family": "gpt-5-5", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.5 (xhigh reasoning tier) on Verified leaderboard runs.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 82.77, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-8-opus-high", "name": "Claude 4.8 Opus (high)", "vendor": "Anthropic", "model_family": "claude-4-8-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.8 Opus (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 82.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-4", "name": "GPT-5.4", "vendor": "openai", "model_family": "gpt-5-4", "parameter_count_b": null, "context_length": 1050000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5.4", "card_summary": "openai GPT-5.4 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 9, "best_success_rate": 82.4, "input_price_per_million": 2.5, "output_price_per_million": 15.0}, {"slug": "claude-4-8-opus-medium", "name": "Claude 4.8 Opus (medium)", "vendor": "Anthropic", "model_family": "claude-4-8-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.8 Opus (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 82.02, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-5-opus-low", "name": "Claude 5 Opus (low)", "vendor": "Anthropic", "model_family": "claude-5-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 5 Opus (low) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 82.02, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "muse-spark-1-2-xhigh", "name": "Muse Spark 1 2 Xhigh", "vendor": "Muse", "model_family": "muse-spark-1-2-xhigh", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Muse Spark 1.2 (xhigh tier) coding model on public SWE benchmarks.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 81.65, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-low", "name": "GPT-5 (low)", "vendor": "OpenAI", "model_family": "gpt-5", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5 (low) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 81.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "minimax-m3", "name": "MiniMax M3", "vendor": "minimax", "model_family": "minimax-m3", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "minimax/minimax-m3", "card_summary": "minimax MiniMax M3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 81.1, "input_price_per_million": 0.3, "output_price_per_million": 1.2}, {"slug": "claude-3-7-sonnet", "name": "Claude 3.7 Sonnet", "vendor": "Anthropic", "model_family": "claude-3-7-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.7 Sonnet on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 23, "best_success_rate": 81.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "openreasoning-nemotron-32b", "name": "OpenReasoning Nemotron 32B", "vendor": "NVIDIA", "model_family": "openreasoning-nemotron-32b", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "NVIDIA OpenReasoning Nemotron 32B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 80.96, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "exaone-4-0-32b", "name": "EXAONE 4.0 32B", "vendor": "LG AI", "model_family": "exaone-4-0-32b", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "LG AI EXAONE 4.0 32B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 80.88, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-exp-1206-whole", "name": "Gemini Exp 1206 (whole)", "vendor": "Google", "model_family": "gemini-exp-1206-whole", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini Exp 1206 (whole) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 80.5, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-235b-a22b", "name": "Qwen3 235B A22B", "vendor": "qwen", "model_family": "qwen3-235b-a22b", "parameter_count_b": 235.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3-235b-a22b", "card_summary": "qwen Qwen3 235B A22B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 80.38, "input_price_per_million": 0.45499999999999996, "output_price_per_million": 1.8199999999999998}, {"slug": "o4", "name": "o4", "vendor": null, "model_family": "o4", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "o4 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 80.09, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-6-opus", "name": "Claude 4.6 Opus", "vendor": "Anthropic", "model_family": "claude-4-6-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.6 Opus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 10, "best_success_rate": 80.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-5-sonnet-high", "name": "Claude 5 Sonnet (high)", "vendor": "Anthropic", "model_family": "claude-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 5 Sonnet (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 80.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-5-2-[high]", "name": "GLM 5.2 [high]", "vendor": "Zhipu", "model_family": "glm-5-2-[high]", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Zhipu GLM 5.2 [high] on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 80.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o1-preview", "name": "o1 preview", "vendor": "OpenAI", "model_family": "o1", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI o1 preview on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 79.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-4-high", "name": "GROK 4 (high)", "vendor": "xAI", "model_family": "grok-4-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 4 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 79.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "swe-1-7-lightning-max", "name": "SWE 1.7 Lightning Max", "vendor": null, "model_family": "swe-1-7-lightning-max", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "SWE 1.7 Lightning Max on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 79.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-4-5", "name": "GROK 4.5", "vendor": "x-ai", "model_family": "grok-4-5", "parameter_count_b": null, "context_length": 500000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "x-ai/grok-4.5", "card_summary": "x-ai GROK 4.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 79.33, "input_price_per_million": 2.0, "output_price_per_million": 6.0}, {"slug": "claude-4-5-opus-medium", "name": "Claude 4.5 Opus (medium)", "vendor": "Anthropic", "model_family": "claude-4-5-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.5 Opus (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 79.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "doubao-seed-code", "name": "Doubao Seed Code", "vendor": "ByteDance", "model_family": "doubao-seed-code", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "ByteDance Doubao Seed Code on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 78.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-haiku", "name": "Claude 3 Haiku", "vendor": "anthropic", "model_family": "claude-3-haiku", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "anthropic/claude-3-haiku", "card_summary": "anthropic Claude 3 Haiku on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 78.75, "input_price_per_million": 0.25, "output_price_per_million": 1.25}, {"slug": "gpt-5-5-medium", "name": "GPT-5.5 (medium)", "vendor": "OpenAI", "model_family": "gpt-5-5", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.5 (medium tier) frontier model on SWE-bench leaderboards.", "is_rl_checkpoint": false, "score_count": 7, "best_success_rate": 78.65, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-3-6-flash-high", "name": "Gemini 3.6 Flash (high)", "vendor": "Google", "model_family": "gemini-3-6-flash", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3.6 Flash (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 78.65, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "opencodereasoning-nemotron-1-1-32b", "name": "OpenCodeReasoning Nemotron 1.1 32B", "vendor": "NVIDIA", "model_family": "opencodereasoning-nemotron-1-1-32b", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "NVIDIA OpenCodeReasoning Nemotron 1.1 32B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 78.53, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-6", "name": "GPT-5.6", "vendor": "OpenAI", "model_family": "gpt-5-6", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.6 Luna base variant (no extra reasoning tier).", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 78.43, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-7-opus-medium", "name": "Claude 4.7 Opus (medium)", "vendor": "Anthropic", "model_family": "claude-4-7-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude Opus 4.7 (medium reasoning tier) for agentic coding.", "is_rl_checkpoint": false, "score_count": 9, "best_success_rate": 78.28, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-6-max", "name": "GPT-5.6 (max)", "vendor": "OpenAI", "model_family": "gpt-5-6", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.6 Luna variant (max tier) on SWE-bench leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 78.28, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-3-mini-high", "name": "GROK 3 Mini (High)", "vendor": "xAI", "model_family": "grok-3-mini-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 3 Mini (High) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 78.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-8-opus-low", "name": "Claude 4.8 Opus (low)", "vendor": "Anthropic", "model_family": "claude-4-8-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.8 Opus (low) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 77.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-6-low", "name": "GPT-5.6 (low)", "vendor": "OpenAI", "model_family": "gpt-5-6", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.6 Sol variant (low tier) for efficient agent loops.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 77.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o3-mini-high", "name": "o3 mini (high)", "vendor": "openai", "model_family": "o3", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/o3-mini-high", "card_summary": "openai o3 mini (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 77.73, "input_price_per_million": 1.1, "output_price_per_million": 4.4}, {"slug": "claude-4-7-opus-max", "name": "Claude 4.7 Opus (max)", "vendor": "Anthropic", "model_family": "claude-4-7-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.7 Opus (max) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 77.53, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o4-mini-low", "name": "o4 mini (low)", "vendor": "OpenAI", "model_family": "o4", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI o4 mini (low) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 77.44, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-5-sonnet-20240620", "name": "Claude 3.5 Sonnet (2024-06-20)", "vendor": "Anthropic", "model_family": "claude-3-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.5 Sonnet (2024-06-20) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 77.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-3-pro-preview", "name": "Gemini 3 Pro Preview", "vendor": "Google", "model_family": "gemini-3-pro-preview", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3 Pro Preview on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 11, "best_success_rate": 77.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "muse-spark-1-1-xhigh", "name": "Muse Spark 1.1 (xhigh)", "vendor": "Muse", "model_family": "muse-spark-1-1-xhigh", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Muse Muse Spark 1.1 (xhigh) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 77.15, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o3", "name": "o3", "vendor": "openai", "model_family": "o3", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/o3", "card_summary": "openai o3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 24, "best_success_rate": 76.9, "input_price_per_million": 2.0, "output_price_per_million": 8.0}, {"slug": "claude-4-5-opus-high", "name": "Claude 4.5 Opus (high)", "vendor": "Anthropic", "model_family": "claude-4-5-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.5 Opus (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 76.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "muse-spark-1-1", "name": "Muse Spark 1.1", "vendor": "meta", "model_family": "muse-spark-1-1", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "meta/muse-spark-1.1", "card_summary": "meta Muse Spark 1.1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 76.18, "input_price_per_million": 1.25, "output_price_per_million": 4.25}, {"slug": "gemini-3-1-pro-high", "name": "Gemini 3.1 Pro (high)", "vendor": "Google", "model_family": "gemini-3-1-pro", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3.1 Pro (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 76.03, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-4-5-[high]", "name": "GROK 4.5 [high]", "vendor": "xAI", "model_family": "grok-4-5-[high]", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 4.5 [high] on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 76.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-3-flash-high", "name": "Gemini 3 Flash (high)", "vendor": "Google", "model_family": "gemini-3-flash", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3 Flash (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 75.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "minimax-m2-5-high", "name": "MiniMax M2.5 (high)", "vendor": "MiniMax", "model_family": "minimax-m2-5-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "MiniMax MiniMax M2.5 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 75.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-2-0-flash", "name": "Gemini 2.0 Flash", "vendor": "Google", "model_family": "gemini-2-0-flash", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 2.0 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 23, "best_success_rate": 75.75, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "minimax-2-7", "name": "Minimax 2.7", "vendor": "MiniMax", "model_family": "minimax-2-7", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "MiniMax Minimax 2.7 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 75.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o3-mini", "name": "o3 mini", "vendor": "openai", "model_family": "o3", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/o3-mini", "card_summary": "openai o3 mini on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 75.36, "input_price_per_million": 1.1, "output_price_per_million": 4.4}, {"slug": "gpt-5-6-medium", "name": "GPT-5.6 (medium)", "vendor": "OpenAI", "model_family": "gpt-5-6", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.6 Luna variant (medium tier) for coding agents.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 75.29, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-5-haiku-20241022", "name": "Claude 3.5 Haiku (2024-10-22)", "vendor": "Anthropic", "model_family": "claude-3-5-haiku", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.5 Haiku (2024-10-22) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 75.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-5-1", "name": "GLM 5 1", "vendor": "Zhipu", "model_family": "glm-5-1", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-5.1", "card_summary": "Zhipu GLM-5.1 bilingual coding model on SWE-bench submissions.", "is_rl_checkpoint": false, "score_count": 11, "best_success_rate": 75.0, "input_price_per_million": 1.26, "output_price_per_million": 3.9600000000000004}, {"slug": "claude-5-sonnet", "name": "Claude 5 Sonnet", "vendor": "Anthropic", "model_family": "claude-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 5 Sonnet on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 74.61, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-3-flash", "name": "Gemini 3 Flash", "vendor": "Google", "model_family": "gemini-3-flash", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 74.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot", "model_family": "kimi-k2-6", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k2.6", "card_summary": "Moonshot KIMI K2.6 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 9, "best_success_rate": 74.6, "input_price_per_million": 0.95, "output_price_per_million": 4.0}, {"slug": "claude-4-6-sonnet", "name": "Claude 4.6 Sonnet", "vendor": "Anthropic", "model_family": "claude-4-6-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.6 Sonnet on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 74.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3-2-exp-reasoner", "name": "DeepSeek V3.2 Exp (Reasoner)", "vendor": "DeepSeek", "model_family": "deepseek-v3-2-exp-reasoner", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3.2 Exp (Reasoner) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 74.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-6-plus", "name": "Qwen3.6 Plus", "vendor": "qwen", "model_family": "qwen3-6-plus", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3.6-plus", "card_summary": "qwen Qwen3.6 Plus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 74.2, "input_price_per_million": 0.325, "output_price_per_million": 1.95}, {"slug": "gemini-3-pro", "name": "Gemini 3 Pro", "vendor": "Google", "model_family": "gemini-3-pro", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 3 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 10, "best_success_rate": 73.93, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-2-codex", "name": "GPT-5.2 codex", "vendor": "openai", "model_family": "gpt-5-2-codex", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5.2-codex", "card_summary": "openai GPT-5.2 codex on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 9, "best_success_rate": 73.8, "input_price_per_million": 1.75, "output_price_per_million": 14.0}, {"slug": "glm-4-7", "name": "GLM 4.7", "vendor": "z-ai", "model_family": "glm-4-7", "parameter_count_b": null, "context_length": 204800, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-4.7", "card_summary": "z-ai GLM 4.7 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 73.4, "input_price_per_million": 0.39999999999999997, "output_price_per_million": 1.75}, {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai", "model_family": "glm-5", "parameter_count_b": null, "context_length": 204800, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-5", "card_summary": "z-ai GLM 5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 11, "best_success_rate": 73.4, "input_price_per_million": 0.6, "output_price_per_million": 1.92}, {"slug": "claude-4-opus", "name": "Claude 4 Opus", "vendor": "Anthropic", "model_family": "claude-4-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4 Opus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 9, "best_success_rate": 73.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", "vendor": "deepseek", "model_family": "deepseek-v4-pro", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "deepseek/deepseek-v4-pro", "card_summary": "deepseek DeepSeek V4 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 73.2, "input_price_per_million": 0.87, "output_price_per_million": 1.74}, {"slug": "deepseek-coder-v2-0724", "name": "DeepSeek Coder V2 0724", "vendor": "DeepSeek", "model_family": "deepseek-coder-v2-0724", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek Coder V2 0724 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 72.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4o-20240513", "name": "GPT-4o (2024-05-13)", "vendor": "OpenAI", "model_family": "gpt-4o", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4o snapshot (May 2024) widely used on early SWE-bench runs.", "is_rl_checkpoint": false, "score_count": 18, "best_success_rate": 72.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen2-5-coder-32b", "name": "Qwen2.5 Coder 32b", "vendor": "Qwen", "model_family": "qwen2-5-coder-32b", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 Coder 32b on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 72.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-5-high", "name": "GLM 5 (high)", "vendor": "Zhipu", "model_family": "glm-5-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Zhipu GLM 5 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 72.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "minimax-m2-5", "name": "MiniMax M2.5", "vendor": "minimax", "model_family": "minimax-m2-5", "parameter_count_b": null, "context_length": 204800, "homepage_url": null, "hf_model_id": null, "openrouter_id": "minimax/minimax-m2.5", "card_summary": "minimax MiniMax M2.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 8, "best_success_rate": 72.6, "input_price_per_million": 0.27, "output_price_per_million": 1.08}, {"slug": "claude-3-opus-20240229", "name": "Claude 3 Opus (2024-02-29)", "vendor": "Anthropic", "model_family": "claude-3-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3 Opus (2024-02-29) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 72.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-5-2", "name": "GLM 5 2", "vendor": "Zhipu", "model_family": "glm-5-2", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-5.2", "card_summary": "Zhipu GLM-5.2 successor with stronger agentic coding scores.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 72.28, "input_price_per_million": 1.19, "output_price_per_million": 3.74}, {"slug": "gpt-5-6-high", "name": "GPT-5.6 (high)", "vendor": "OpenAI", "model_family": "gpt-5-6", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.6 Sol variant (high tier) on public coding benchmarks.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 72.28, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "chatgpt-4o", "name": "ChatGPT-4o", "vendor": "OpenAI", "model_family": "chatgpt-4o", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI ChatGPT-4o on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 72.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v2-5", "name": "DeepSeek V2.5", "vendor": "DeepSeek", "model_family": "deepseek-v2-5", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V2.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 72.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v2-5-1210", "name": "DeepSeek V2.5 1210", "vendor": "DeepSeek", "model_family": "deepseek-v2-5-1210", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V2.5 1210 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 72.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-opus-thinking", "name": "Claude 4 Opus (thinking)", "vendor": "Anthropic", "model_family": "claude-4-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4 Opus (thinking) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 72.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-5-sonnet-high", "name": "Claude 4.5 Sonnet (high)", "vendor": "Anthropic", "model_family": "claude-4-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.5 Sonnet (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 11, "best_success_rate": 72.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5", "name": "GPT-5", "vendor": "openai", "model_family": "gpt-5", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5", "card_summary": "OpenAI GPT-5 flagship model for frontier coding agent benchmarks.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 71.8, "input_price_per_million": 1.25, "output_price_per_million": 10.0}, {"slug": "gpt-5-2-high", "name": "GPT-5.2 (high)", "vendor": "OpenAI", "model_family": "gpt-5-2", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.2 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 71.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3-2-reasoner", "name": "DeepSeek V3.2 Reasoner", "vendor": "DeepSeek", "model_family": "deepseek-v3-2-reasoner", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3.2 Reasoner on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 7, "best_success_rate": 71.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-7-plus-thinking", "name": "Qwen3.7 Plus (thinking)", "vendor": "Qwen", "model_family": "qwen3-7-plus-thinking", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3.7 Plus (thinking) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 71.54, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4o-20240806", "name": "GPT-4o (2024-08-06)", "vendor": "OpenAI", "model_family": "gpt-4o", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4o (2024-08-06) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 12, "best_success_rate": 71.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4o-20241120", "name": "GPT-4o (2024-11-20)", "vendor": "OpenAI", "model_family": "gpt-4o", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4o (2024-11-20) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 71.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen2-5-coder-32b-instruct", "name": "Qwen2.5 Coder 32B Instruct", "vendor": "qwen", "model_family": "qwen2-5-coder-32b-instruct", "parameter_count_b": 32.0, "context_length": 32768, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen-2.5-coder-32b-instruct", "card_summary": "qwen Qwen2.5 Coder 32B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 71.4, "input_price_per_million": 0.66, "output_price_per_million": 1.0}, {"slug": "lingxi-kimi", "name": "Lingxi KIMI", "vendor": "Moonshot", "model_family": "lingxi-kimi", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Moonshot Lingxi KIMI on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 71.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k2-5-high", "name": "KIMI K2.5 (high)", "vendor": "Moonshot", "model_family": "kimi-k2-5-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Moonshot KIMI K2.5 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 70.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-6-xhigh", "name": "GPT-5.6 (xhigh)", "vendor": "OpenAI", "model_family": "gpt-5-6", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.6 Luna variant (xhigh tier) for frontier agent scores.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 70.79, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o3-mini-low", "name": "o3 mini (low)", "vendor": "OpenAI", "model_family": "o3", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI o3 mini (low) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 70.62, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3-2-exp-chat", "name": "DeepSeek V3.2 Exp (Chat)", "vendor": "DeepSeek", "model_family": "deepseek-v3-2-exp-chat", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3.2 Exp (Chat) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 70.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v4-pro-high", "name": "Deepseek V4 Pro High", "vendor": "DeepSeek", "model_family": "deepseek-v4-pro-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek V4 Pro (high tier) on public coding leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 70.04, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3-2-high", "name": "DeepSeek V3.2 (high)", "vendor": "DeepSeek", "model_family": "deepseek-v3-2-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3.2 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 70.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-4-medium", "name": "GPT-5.4 (medium)", "vendor": "OpenAI", "model_family": "gpt-5-4", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.4 (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 70.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-chat-v2-0628", "name": "DeepSeek Chat V2 0628", "vendor": "DeepSeek", "model_family": "deepseek-chat-v2-0628", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek Chat V2 0628 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 69.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-coder-480b-a35b-instruct", "name": "Qwen3 Coder 480B A35B Instruct", "vendor": "Qwen", "model_family": "qwen3-coder-480b-a35b-instruct", "parameter_count_b": 480.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3 Coder 480B A35B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 69.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-exp-1206-diff", "name": "Gemini Exp 1206 (diff)", "vendor": "Google", "model_family": "gemini-exp-1206-diff", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini Exp 1206 (diff) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 69.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k2-thinking", "name": "KIMI K2 Thinking", "vendor": "moonshotai", "model_family": "kimi-k2-thinking", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k2-thinking", "card_summary": "moonshotai KIMI K2 Thinking on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 8, "best_success_rate": 69.2, "input_price_per_million": 0.6, "output_price_per_million": 2.5}, {"slug": "qwen2-5-coder-14b-instruct", "name": "Qwen2.5 Coder 14B Instruct", "vendor": "Qwen", "model_family": "qwen2-5-coder-14b-instruct", "parameter_count_b": 14.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 Coder 14B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 69.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai", "model_family": "kimi-k2-5", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k2.5", "card_summary": "moonshotai KIMI K2.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 8, "best_success_rate": 68.8, "input_price_per_million": 0.6, "output_price_per_million": 3.0}, {"slug": "minimax-m2-1", "name": "MiniMax M2.1", "vendor": "minimax", "model_family": "minimax-m2-1", "parameter_count_b": null, "context_length": 204800, "homepage_url": null, "hf_model_id": null, "openrouter_id": "minimax/minimax-m2.1", "card_summary": "minimax MiniMax M2.1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 68.8, "input_price_per_million": 0.3, "output_price_per_million": 1.2}, {"slug": "claude-4-sonnet-thinking", "name": "Claude 4 Sonnet (thinking)", "vendor": "Anthropic", "model_family": "claude-4-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4 Sonnet (thinking) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 68.53, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-1-opus-high", "name": "Claude 4.1 Opus (high)", "vendor": "Anthropic", "model_family": "claude-4-1-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.1 Opus (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 12, "best_success_rate": 68.48, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm4-6", "name": "Glm4 6", "vendor": "Zhipu", "model_family": "glm4-6", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Zhipu Glm4 6 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 68.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "composer-2-5", "name": "Composer 2 5", "vendor": "Cursor", "model_family": "composer-2-5", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Cursor Composer 2.5 coding model for agent harnesses.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 67.79, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "composer-2-5-fast", "name": "Composer 2 5 Fast", "vendor": "Cursor", "model_family": "composer-2-5-fast", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Cursor Composer 2.5 Fast \u2014 lower-latency variant for agent loops.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 67.79, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v4-flash-0731-max", "name": "Deepseek V4 Flash 0731 Max", "vendor": "DeepSeek", "model_family": "deepseek-v4-flash-0731-max", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek V4 Flash (July snapshot, max tier) for SWE agent runs.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 67.79, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-0613", "name": "GPT-4.0613", "vendor": "OpenAI", "model_family": "gpt-4-0613", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4.0613 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 67.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-6-sonnet-medium", "name": "Claude 4.6 Sonnet (medium)", "vendor": "Anthropic", "model_family": "claude-4-6-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.6 Sonnet (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 67.42, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-6-opus-high", "name": "Claude 4.6 Opus (high)", "vendor": "Anthropic", "model_family": "claude-4-6-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.6 Opus (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 67.33, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "dracarys2-72b-instruct", "name": "Dracarys2 72B Instruct", "vendor": "Abacus", "model_family": "dracarys2-72b-instruct", "parameter_count_b": 72.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Abacus Dracarys2 72B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 66.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-7-opus-high", "name": "Claude 4.7 Opus (high)", "vendor": "Anthropic", "model_family": "claude-4-7-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.7 Opus (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 66.67, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-5-haiku-high", "name": "Claude 4.5 Haiku (high)", "vendor": "Anthropic", "model_family": "claude-4-5-haiku", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.5 Haiku (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 66.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-coder-next", "name": "Qwen3 Coder Next", "vendor": "qwen", "model_family": "qwen3-coder-next", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3-coder-next", "card_summary": "qwen Qwen3 Coder Next on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 66.6, "input_price_per_million": 0.12, "output_price_per_million": 0.7999999999999999}, {"slug": "gpt-5-2025-medium", "name": "GPT-5.2025 (medium)", "vendor": "OpenAI", "model_family": "gpt-5-2025", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.2025 (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 66.36, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-0125", "name": "GPT-4.0125", "vendor": "OpenAI", "model_family": "gpt-4-0125", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4.0125 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 66.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-0314", "name": "GPT-4.0314", "vendor": "OpenAI", "model_family": "gpt-4-0314", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4.0314 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 66.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama-3-1-405b-instruct-whole", "name": "Llama 3.1 405b Instruct (whole)", "vendor": "Meta", "model_family": "llama-3-1-405b-instruct-whole", "parameter_count_b": 405.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama 3.1 405b Instruct (whole) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 66.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-1-medium", "name": "GPT-5.1 (medium)", "vendor": "OpenAI", "model_family": "gpt-5-1", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.1 (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 66.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-1-codex-medium", "name": "GPT-5.1 codex (medium)", "vendor": "OpenAI", "model_family": "gpt-5-1-codex", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.1 codex (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 66.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-1-codex-max", "name": "GPT-5.1 codex (max)", "vendor": "openai", "model_family": "gpt-5-1-codex", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5.1-codex-max", "card_summary": "openai GPT-5.1 codex (max) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 65.45, "input_price_per_million": 1.25, "output_price_per_million": 10.0}, {"slug": "gpt-4-1106", "name": "GPT-4.1106", "vendor": "OpenAI", "model_family": "gpt-4-1106", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4.1106 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 65.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-1-5-pro", "name": "Gemini 1.5 Pro", "vendor": "Google", "model_family": "gemini-1-5-pro", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 1.5 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 65.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k2", "name": "KIMI K2", "vendor": "moonshotai", "model_family": "kimi-k2", "parameter_count_b": null, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k2", "card_summary": "moonshotai KIMI K2 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 65.4, "input_price_per_million": 0.5700000000000001, "output_price_per_million": 2.3}, {"slug": "mistral-large-2411", "name": "Mistral Large (2411)", "vendor": "Mistral", "model_family": "mistral-large-2411", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Mistral Large (2411) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 65.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen-2-5-72b-instruct-bf16", "name": "QWEN 2.5 72b Instruct (bf16)", "vendor": "Qwen", "model_family": "qwen-2-5-72b-instruct-bf16", "parameter_count_b": 72.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen QWEN 2.5 72b Instruct (bf16) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 65.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen-qwen-2-5-coder-32b-instruct", "name": "Qwen/qwen 2.5 Coder 32b Instruct", "vendor": "Qwen", "model_family": "qwen-qwen-2-5-coder-32b-instruct", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen/qwen 2.5 Coder 32b Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 65.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "yi-lightning", "name": "Yi Lightning", "vendor": "01.AI", "model_family": "yi-lightning", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "01.AI Yi Lightning on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 65.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-7-sonnet-thinking-20250219", "name": "Claude 3.7 Sonnet (thinking) (2025-02-19)", "vendor": "Anthropic", "model_family": "claude-3-7-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.7 Sonnet (thinking) (2025-02-19) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 64.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-opus-high", "name": "Claude 4 Opus (high)", "vendor": "Anthropic", "model_family": "claude-4-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4 Opus (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 64.85, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-5-haiku", "name": "Claude 4.5 Haiku", "vendor": "Anthropic", "model_family": "claude-4-5-haiku", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.5 Haiku on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 6, "best_success_rate": 64.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-3-1-pro-preview", "name": "Gemini 3.1 Pro Preview", "vendor": "google", "model_family": "gemini-3-1-pro-preview", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemini-3.1-pro-preview", "card_summary": "google Gemini 3.1 Pro Preview on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 64.67, "input_price_per_million": 2.0, "output_price_per_million": 12.0}, {"slug": "claude-3-7-sonnet-high", "name": "Claude 3.7 Sonnet (high)", "vendor": "Anthropic", "model_family": "claude-3-7-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.7 Sonnet (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 17, "best_success_rate": 64.24, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-4-1-opus", "name": "Claude 4.1 Opus", "vendor": "Anthropic", "model_family": "claude-4-1-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4.1 Opus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 14, "best_success_rate": 64.24, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm4-5", "name": "Glm4 5", "vendor": "Zhipu", "model_family": "glm4-5", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Zhipu Glm4 5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 64.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3-2", "name": "DeepSeek V3.2", "vendor": "deepseek", "model_family": "deepseek-v3-2", "parameter_count_b": null, "context_length": 163840, "homepage_url": null, "hf_model_id": null, "openrouter_id": "deepseek/deepseek-v3.2", "card_summary": "deepseek DeepSeek V3.2 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 64.0, "input_price_per_million": 0.26, "output_price_per_million": 0.38}, {"slug": "gpt-5-3-codex", "name": "GPT-5.3 codex", "vendor": "openai", "model_family": "gpt-5-3-codex", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5.3-codex", "card_summary": "openai GPT-5.3 codex on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 64.0, "input_price_per_million": 1.75, "output_price_per_million": 14.0}, {"slug": "llama-3-1-405b-instruct-diff", "name": "Llama 3.1 405b Instruct (diff)", "vendor": "Meta", "model_family": "llama-3-1-405b-instruct-diff", "parameter_count_b": 405.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama 3.1 405b Instruct (diff) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 63.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "nousresearch-hermes-3-llama-3-1-405b", "name": "Nousresearch/hermes 3 Llama 3.1 405b", "vendor": "nousresearch", "model_family": "nousresearch-hermes-3-llama-3-1-405b", "parameter_count_b": 405.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "nousresearch/hermes-3-llama-3.1-405b", "card_summary": "nousresearch Nousresearch/hermes 3 Llama 3.1 405b on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 63.9, "input_price_per_million": 1.0, "output_price_per_million": 1.0}, {"slug": "qwen2-5-1-coder-7b-instruct-gguf-q8-0-32k", "name": "Qwen2.5.1 Coder 7B Instruct GGUF Q8 0 32k", "vendor": "Qwen", "model_family": "qwen2-5-1-coder-7b-instruct-gguf-q8-0-32k", "parameter_count_b": 7.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5.1 Coder 7B Instruct GGUF Q8 0 32k on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 63.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-3-flash-preview", "name": "Gemini 3 Flash Preview", "vendor": "google", "model_family": "gemini-3-flash-preview", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemini-3-flash-preview", "card_summary": "google Gemini 3 Flash Preview on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 63.33, "input_price_per_million": 0.5, "output_price_per_million": 3.0}, {"slug": "claude-3-7-sonnet-20250224", "name": "Claude 3.7 Sonnet (2025-02-24)", "vendor": "Anthropic", "model_family": "claude-3-7-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.7 Sonnet (2025-02-24) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 63.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v4-pro-0813-max", "name": "Deepseek V4 Pro 0813 Max", "vendor": "DeepSeek", "model_family": "deepseek-v4-pro-0813-max", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek V4 Pro August snapshot (max tier) for agentic coding.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 62.92, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4o", "name": "GPT-4o", "vendor": "openai", "model_family": "gpt-4o", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-4o", "card_summary": "openai GPT-4o on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 62.9, "input_price_per_million": 2.5, "output_price_per_million": 10.0}, {"slug": "gpt-5-3-codex-xhigh", "name": "GPT-5.3 codex (xhigh)", "vendor": "OpenAI", "model_family": "gpt-5-3-codex", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.3 codex (xhigh) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 62.67, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-5-27b", "name": "Qwen3.5 27B", "vendor": "qwen", "model_family": "qwen3-5-27b", "parameter_count_b": 27.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3.5-27b", "card_summary": "qwen Qwen3.5 27B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 62.67, "input_price_per_million": 0.195, "output_price_per_million": 1.56}, {"slug": "qwen3-5-397b-a17b", "name": "Qwen3.5 397B A17B", "vendor": "qwen", "model_family": "qwen3-5-397b-a17b", "parameter_count_b": 397.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3.5-397b-a17b", "card_summary": "qwen Qwen3.5 397B A17B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 62.67, "input_price_per_million": 0.39, "output_price_per_million": 2.34}, {"slug": "qwen3-coder-480b", "name": "Qwen3 Coder 480B", "vendor": "Qwen", "model_family": "qwen3-coder-480b", "parameter_count_b": 480.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3 Coder 480B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 62.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "swe-search", "name": "SWE Search", "vendor": "Princeton NLP", "model_family": "swe-search", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Princeton NLP SWE Search on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 62.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "nemotron-3-super", "name": "Nemotron 3 Super", "vendor": "NVIDIA", "model_family": "nemotron-3-super", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "NVIDIA Nemotron 3 Super on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 62.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-5-flash", "name": "Qwen3.5 Flash", "vendor": "Qwen", "model_family": "qwen3-5-flash", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3.5 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 62.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "step-3-5-flash", "name": "Step 3.5 Flash", "vendor": "stepfun", "model_family": "step-3-5-flash", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "stepfun/step-3.5-flash", "card_summary": "stepfun Step 3.5 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 62.0, "input_price_per_million": 0.09999999999999999, "output_price_per_million": 0.3}, {"slug": "qwen2-5-coder-14b", "name": "Qwen2.5 Coder 14b", "vendor": "Qwen", "model_family": "qwen2-5-coder-14b", "parameter_count_b": 14.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 Coder 14b on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 61.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o1-high", "name": "o1 (high)", "vendor": "OpenAI", "model_family": "o1", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI o1 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 61.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "mimo-v2-5-pro", "name": "MiMo V2.5 Pro", "vendor": "xiaomi", "model_family": "mimo-v2-5-pro", "parameter_count_b": null, "context_length": 1050000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "xiaomi/mimo-v2.5-pro", "card_summary": "xiaomi MiMo V2.5 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 61.54, "input_price_per_million": 0.435, "output_price_per_million": 0.87}, {"slug": "gpt-5-2025-high", "name": "GPT-5.2025 (high)", "vendor": "OpenAI", "model_family": "gpt-5-2025", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.2025 (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 61.43, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "minimax-m2", "name": "MiniMax M2", "vendor": "minimax", "model_family": "minimax-m2", "parameter_count_b": null, "context_length": 204800, "homepage_url": null, "hf_model_id": null, "openrouter_id": "minimax/minimax-m2", "card_summary": "minimax MiniMax M2 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 61.0, "input_price_per_million": 0.255, "output_price_per_million": 1.02}, {"slug": "gemini-exp-1114", "name": "Gemini Exp 1114", "vendor": "Google", "model_family": "gemini-exp-1114", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini Exp 1114 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 60.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-5-sonnet", "name": "Claude 3.5 Sonnet", "vendor": "Anthropic", "model_family": "claude-3-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.5 Sonnet (leaderboard naming variant).", "is_rl_checkpoint": false, "score_count": 12, "best_success_rate": 60.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "mistral-large-2-2407", "name": "Mistral Large 2 (2407)", "vendor": "Mistral", "model_family": "mistral-large-2-2407", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Mistral Large 2 (2407) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 60.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-codex", "name": "GPT-5 codex", "vendor": "OpenAI", "model_family": "gpt-5-codex", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5 codex on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 60.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-1-codex", "name": "GPT-5.1 codex", "vendor": "openai", "model_family": "gpt-5-1-codex", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5.1-codex", "card_summary": "openai GPT-5.1 codex on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 60.0, "input_price_per_million": 1.25, "output_price_per_million": 10.0}, {"slug": "gpt-5-mini-medium", "name": "GPT-5 mini (medium)", "vendor": "OpenAI", "model_family": "gpt-5-mini", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5 mini (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 59.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-235b-a22b-diff-no-think-alibaba-api", "name": "Qwen3 235B A22B Diff, No Think, Alibaba API", "vendor": "Qwen", "model_family": "qwen3-235b-a22b-diff-no-think-alibaba-api", "parameter_count_b": 235.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3 235B A22B Diff, No Think, Alibaba API on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 59.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama-3-3-70b-instruct", "name": "Llama 3.3 70B Instruct", "vendor": "meta-llama", "model_family": "llama-3-3-70b-instruct", "parameter_count_b": 70.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "meta-llama/llama-3.3-70b-instruct", "card_summary": "meta-llama Llama 3.3 70B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 59.4, "input_price_per_million": 0.71, "output_price_per_million": 0.71}, {"slug": "grok-2", "name": "GROK 2", "vendor": "xAI", "model_family": "grok-2", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 2 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 58.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama-3-1-70b-instruct", "name": "Llama 3.1 70b Instruct", "vendor": "meta-llama", "model_family": "llama-3-1-70b-instruct", "parameter_count_b": 70.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "meta-llama/llama-3.1-70b-instruct", "card_summary": "meta-llama Llama 3.1 70b Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 58.6, "input_price_per_million": 0.39999999999999997, "output_price_per_million": 0.39999999999999997}, {"slug": "qwen2-5-32b-instruct-q8-0", "name": "Qwen2.5 32b Instruct Q8 0", "vendor": "Qwen", "model_family": "qwen2-5-32b-instruct-q8-0", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 32b Instruct Q8 0 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 58.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-exp-1121", "name": "Gemini Exp 1121", "vendor": "Google", "model_family": "gemini-exp-1121", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini Exp 1121 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 57.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen2-5-coder-7b-instruct", "name": "Qwen2.5 Coder 7B Instruct", "vendor": "Qwen", "model_family": "qwen2-5-coder-7b-instruct", "parameter_count_b": 7.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 Coder 7B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 57.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-r1", "name": "Deepseek R1", "vendor": "deepseek", "model_family": "deepseek-r1", "parameter_count_b": null, "context_length": 64000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "deepseek/deepseek-r1", "card_summary": "deepseek Deepseek R1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 56.9, "input_price_per_million": 0.7, "output_price_per_million": 2.5}, {"slug": "trinity-large-thinking", "name": "Trinity Large Thinking", "vendor": "arcee-ai", "model_family": "trinity-large-thinking", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "arcee-ai/trinity-large-thinking", "card_summary": "arcee-ai Trinity Large Thinking on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 56.8, "input_price_per_million": 0.22, "output_price_per_million": 0.85}, {"slug": "qwen3-5-35b-a3b", "name": "Qwen3.5 35B A3B", "vendor": "qwen", "model_family": "qwen3-5-35b-a3b", "parameter_count_b": 35.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3.5-35b-a3b", "card_summary": "qwen Qwen3.5 35B A3B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 56.67, "input_price_per_million": 0.25, "output_price_per_million": 1.25}, {"slug": "deepseek-v3-2-speciale", "name": "Deepseek V3.2 Speciale", "vendor": "DeepSeek", "model_family": "deepseek-v3-2-speciale", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek Deepseek V3.2 Speciale on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 56.44, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "devstral-small-2512", "name": "Devstral Small (2512)", "vendor": "Mistral", "model_family": "devstral-small-2512", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Devstral Small (2512) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 56.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-mini", "name": "GPT-5 mini", "vendor": "openai", "model_family": "gpt-5-mini", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-5-mini", "card_summary": "openai GPT-5 mini on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 56.2, "input_price_per_million": 0.25, "output_price_per_million": 2.0}, {"slug": "gpt-3-5", "name": "GPT-3.5", "vendor": "OpenAI", "model_family": "gpt-3-5", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-3.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 56.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen2-72b-instruct", "name": "Qwen2 72B Instruct", "vendor": "Qwen", "model_family": "qwen2-72b-instruct", "parameter_count_b": 72.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2 72B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 55.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-4-6-t=1", "name": "GLM 4.6 (T=1)", "vendor": "Zhipu", "model_family": "glm-4-6-t=1", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Zhipu GLM 4.6 (T=1) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 55.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3-0324", "name": "DeepSeek V3 0324", "vendor": "DeepSeek", "model_family": "deepseek-v3-0324", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3 0324 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 55.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-2-5-flash-preview", "name": "Gemini 2.5 Flash Preview", "vendor": "Google", "model_family": "gemini-2-5-flash-preview", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 2.5 Flash Preview on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 55.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-sonnet-20240229", "name": "Claude 3 Sonnet (2024-02-29)", "vendor": "Anthropic", "model_family": "claude-3-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3 Sonnet (2024-02-29) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 54.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-2-mini", "name": "GROK 2 Mini", "vendor": "xAI", "model_family": "grok-2-mini", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 2 Mini on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 54.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama-3-1-nemotron-70b-instruct-hf", "name": "Llama 3.1 Nemotron 70B Instruct HF", "vendor": "Meta", "model_family": "llama-3-1-nemotron-70b-instruct-hf", "parameter_count_b": 70.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama 3.1 Nemotron 70B Instruct HF on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 54.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "quasar-alpha", "name": "Quasar Alpha", "vendor": "OpenRouter", "model_family": "quasar-alpha", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenRouter Quasar Alpha on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 54.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k2-instruct-0905", "name": "KIMI K2 Instruct 0905", "vendor": "Moonshot", "model_family": "kimi-k2-instruct-0905", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Moonshot KIMI K2 Instruct 0905 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 54.29, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-4-5-2025-08-22", "name": "GLM 4.5 (2025 08 22)", "vendor": "Zhipu", "model_family": "glm-4-5-2025-08-22", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Zhipu GLM 4.5 (2025 08 22) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 54.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "nova-pro", "name": "Nova Pro", "vendor": "Amazon", "model_family": "nova-pro", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Amazon Nova Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 54.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen2-5-32b", "name": "Qwen2.5 32b", "vendor": "Qwen", "model_family": "qwen2-5-32b", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 32b on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 54.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "minimax-m2-7", "name": "MiniMax M2.7", "vendor": "minimax", "model_family": "minimax-m2-7", "parameter_count_b": null, "context_length": 204800, "homepage_url": null, "hf_model_id": null, "openrouter_id": "minimax/minimax-m2.7", "card_summary": "minimax MiniMax M2.7 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 54.0, "input_price_per_million": 0.3, "output_price_per_million": 1.2}, {"slug": "devstral-2512", "name": "Devstral (2512)", "vendor": "mistralai", "model_family": "devstral-2512", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "mistralai/devstral-2512", "card_summary": "mistralai Devstral (2512) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 53.8, "input_price_per_million": 0.44, "output_price_per_million": 2.2}, {"slug": "gemini-2-5-pro-20250506", "name": "Gemini 2.5 Pro (2025-05-06)", "vendor": "Google", "model_family": "gemini-2-5-pro", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 2.5 Pro (2025-05-06) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 53.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "codesweep-sweagent-kimi-k2", "name": "Codesweep Sweagent KIMI K2", "vendor": "Moonshot", "model_family": "codesweep-sweagent-kimi-k2", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Moonshot Codesweep Sweagent KIMI K2 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 53.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-3-beta", "name": "GROK 3 Beta", "vendor": "xAI", "model_family": "grok-3-beta", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 3 Beta on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 53.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "optimus-alpha", "name": "Optimus Alpha", "vendor": "OpenAI", "model_family": "optimus-alpha", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI Optimus Alpha on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 52.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-7-sonnet-20250219", "name": "Claude 3.7 Sonnet (2025-02-19)", "vendor": "Anthropic", "model_family": "claude-3-7-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.7 Sonnet (2025-02-19) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 52.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "devstral-2-123b-instruct-2512", "name": "Devstral 2 123B Instruct 2512", "vendor": "Mistral", "model_family": "devstral-2-123b-instruct-2512", "parameter_count_b": 123.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Devstral 2 123B Instruct 2512 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 52.73, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-1", "name": "GPT-4.1", "vendor": "openai", "model_family": "gpt-4-1", "parameter_count_b": null, "context_length": 1047576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-4.1", "card_summary": "openai GPT-4.1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 19, "best_success_rate": 52.4, "input_price_per_million": 2.0, "output_price_per_million": 8.0}, {"slug": "gemini-2-0-flash-20241212", "name": "Gemini 2.0 Flash (2024-12-12)", "vendor": "Google", "model_family": "gemini-2-0-flash", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 2.0 Flash (2024-12-12) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 52.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-coder-30b-a3b-instruct", "name": "Qwen3 Coder 30B A3B Instruct", "vendor": "qwen", "model_family": "qwen3-coder-30b-a3b-instruct", "parameter_count_b": 30.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3-coder-30b-a3b-instruct", "card_summary": "qwen Qwen3 Coder 30B A3B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 52.2, "input_price_per_million": 0.07, "output_price_per_million": 0.28}, {"slug": "qwen2-5-coder-7b-instruct-q8-0", "name": "Qwen2.5 Coder 7b Instruct Q8 0", "vendor": "Qwen", "model_family": "qwen2-5-coder-7b-instruct-q8-0", "parameter_count_b": 7.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 Coder 7b Instruct Q8 0 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 51.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-1-20250414", "name": "GPT-4.1 (2025-04-14)", "vendor": "OpenAI", "model_family": "gpt-4-1", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4.1 (2025-04-14) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 51.58, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-4-5", "name": "GLM 4.5", "vendor": "z-ai", "model_family": "glm-4-5", "parameter_count_b": null, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-4.5", "card_summary": "z-ai GLM 4.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 51.43, "input_price_per_million": 0.6, "output_price_per_million": 2.2}, {"slug": "codestral-2405", "name": "Codestral 2405", "vendor": "Mistral", "model_family": "codestral-2405", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Codestral 2405 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 51.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-4", "name": "GROK 4", "vendor": "xAI", "model_family": "grok-4", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 4 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 50.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "hy3", "name": "Hy3", "vendor": "tencent", "model_family": "hy3", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "tencent/hy3", "card_summary": "tencent Hy3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 49.7, "input_price_per_million": 0.0825, "output_price_per_million": 0.33}, {"slug": "glm-4-6", "name": "GLM 4.6", "vendor": "z-ai", "model_family": "glm-4-6", "parameter_count_b": null, "context_length": 204800, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-4.6", "card_summary": "z-ai GLM 4.6 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 49.6, "input_price_per_million": 0.43, "output_price_per_million": 1.75}, {"slug": "qwen2-72b-instruct-q8-0", "name": "Qwen2 72b Instruct Q8 0", "vendor": "Qwen", "model_family": "qwen2-72b-instruct-q8-0", "parameter_count_b": 72.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2 72b Instruct Q8 0 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 49.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek", "model_family": "deepseek-v3", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 49.55, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-3-mini-beta-high", "name": "GROK 3 Mini Beta (high)", "vendor": "xAI", "model_family": "grok-3-mini-beta-high", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 3 Mini Beta (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 49.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama3-70b-8192", "name": "Llama3 70b 8192", "vendor": "Meta", "model_family": "llama3-70b-8192", "parameter_count_b": 70.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama3 70b 8192 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 49.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v4-pro-[high]", "name": "DeepSeek V4 Pro [high]", "vendor": "DeepSeek", "model_family": "deepseek-v4-pro-[high]", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V4 Pro [high] on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 48.97, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-code-fast-1", "name": "GROK Code Fast 1", "vendor": "xAI", "model_family": "grok-code-fast-1", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK Code Fast 1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 48.57, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-chat-v3-prev", "name": "DeepSeek Chat V3 (prev)", "vendor": "DeepSeek", "model_family": "deepseek-chat-v3-prev", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek Chat V3 (prev) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 48.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "codestral-22b-v0-1-q4-k-m", "name": "Codestral 22B V0.1 Q4 K M", "vendor": "Mistral", "model_family": "codestral-22b-v0-1-q4-k-m", "parameter_count_b": 22.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Codestral 22B V0.1 Q4 K M on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 48.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "codestral-22b-v0-1-q8-0", "name": "Codestral 22b V0.1 Q8 0", "vendor": "Mistral", "model_family": "codestral-22b-v0-1-q8-0", "parameter_count_b": 22.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Codestral 22b V0.1 Q8 0 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 48.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "mimo-v2-pro", "name": "MiMo V2 Pro", "vendor": "Xiaomi", "model_family": "mimo-v2-pro", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Xiaomi MiMo V2 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 48.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-8-27b", "name": "Qwen3.8 27B", "vendor": "qwen", "model_family": "qwen3-8-27b", "parameter_count_b": 27.0, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3.8-27b", "card_summary": "qwen Qwen3.8 27B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 48.0, "input_price_per_million": 0.425, "output_price_per_million": 2.5500000000000003}, {"slug": "glm-4-5-air", "name": "GLM 4.5 Air", "vendor": "z-ai", "model_family": "glm-4-5-air", "parameter_count_b": null, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-4.5-air", "card_summary": "z-ai GLM 4.5 Air on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 47.91, "input_price_per_million": 0.13, "output_price_per_million": 0.85}, {"slug": "muse-glimmer-30b", "name": "Muse Glimmer 30B", "vendor": "meta", "model_family": "muse-glimmer-30b", "parameter_count_b": 30.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "meta/muse-glimmer-30b", "card_summary": "meta Muse Glimmer 30B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 47.6, "input_price_per_million": 0.35, "output_price_per_million": 1.5}, {"slug": "claude-3-haiku-20240307", "name": "Claude 3 Haiku (2024-03-07)", "vendor": "Anthropic", "model_family": "claude-3-haiku", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3 Haiku (2024-03-07) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 47.4, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k2-7-code", "name": "KIMI K2.7 Code", "vendor": "moonshotai", "model_family": "kimi-k2-7-code", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k2.7-code", "card_summary": "moonshotai KIMI K2.7 Code on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 46.9, "input_price_per_million": 0.66, "output_price_per_million": 3.4}, {"slug": "devstral-small-2505", "name": "Devstral Small 2505", "vendor": "Mistral", "model_family": "devstral-small-2505", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Devstral Small 2505 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 46.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-oss-120b-high", "name": "GPT Oss 120b High", "vendor": "OpenAI", "model_family": "gpt-oss-120b-high", "parameter_count_b": 120.0, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT Oss 120b High on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 46.67, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemma-4-31b", "name": "Gemma 4 31B", "vendor": "Google", "model_family": "gemma-4-31b", "parameter_count_b": 31.0, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemma 4 31B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 46.67, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-5-mini-high", "name": "GPT-5 mini (high)", "vendor": "OpenAI", "model_family": "gpt-5-mini", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5 mini (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 46.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "co-patcher", "name": "Co PatcheR", "vendor": "Co-Patcher", "model_family": "co-patcher", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Co-Patcher Co PatcheR on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 46.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "codestral", "name": "Codestral", "vendor": "Meta", "model_family": "codestral", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Codestral on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 45.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "chatgpt-4o-20250329", "name": "ChatGPT-4o (2025-03-29)", "vendor": "OpenAI", "model_family": "chatgpt-4o", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI ChatGPT-4o (2025-03-29) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 45.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "yi-coder-9b-chat-q4-0", "name": "Yi Coder 9b Chat Q4 0", "vendor": "01.AI", "model_family": "yi-coder-9b-chat-q4-0", "parameter_count_b": 9.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "01.AI Yi Coder 9b Chat Q4 0 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 45.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-5", "name": "GPT-4.5", "vendor": "OpenAI", "model_family": "gpt-4-5", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 44.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "o1-mini", "name": "o1 mini", "vendor": "OpenAI", "model_family": "o1", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI o1 mini on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 44.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "intern-s2-preview-397b", "name": "Intern S2 Preview 397B", "vendor": "InternLM", "model_family": "intern-s2-preview-397b", "parameter_count_b": 397.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "InternLM Intern S2 Preview 397B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 44.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "wizardlm-2-8x22b", "name": "WizardLM 2 8x22B", "vendor": "microsoft", "model_family": "wizardlm-2-8x22b", "parameter_count_b": null, "context_length": 65535, "homepage_url": null, "hf_model_id": null, "openrouter_id": "microsoft/wizardlm-2-8x22b", "card_summary": "microsoft WizardLM 2 8x22B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 44.4, "input_price_per_million": 0.62, "output_price_per_million": 0.62}, {"slug": "deepseek-v3-march-2025", "name": "DeepSeek V3 (March 2025)", "vendor": "DeepSeek", "model_family": "deepseek-v3-march-2025", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3 (March 2025) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 16, "best_success_rate": 44.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "kimi-k2-instruct", "name": "KIMI K2 Instruct", "vendor": "Moonshot", "model_family": "kimi-k2-instruct", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Moonshot KIMI K2 Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 43.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "yi-coder-9b-chat", "name": "Yi Coder 9b Chat", "vendor": "Meta", "model_family": "yi-coder-9b-chat", "parameter_count_b": 9.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Yi Coder 9b Chat on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 43.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v4-flash-[high]", "name": "DeepSeek V4 Flash [high]", "vendor": "DeepSeek", "model_family": "deepseek-v4-flash-[high]", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V4 Flash [high] on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 43.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-6-27b", "name": "Qwen3.6 27B", "vendor": "qwen", "model_family": "qwen3-6-27b", "parameter_count_b": 27.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3.6-27b", "card_summary": "qwen Qwen3.6 27B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 43.2, "input_price_per_million": 0.6, "output_price_per_million": 3.5999999999999996}, {"slug": "gpt-5-2025", "name": "GPT-5.2025", "vendor": "OpenAI", "model_family": "gpt-5-2025", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5.2025 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 42.86, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "reflection-70b", "name": "Reflection 70B", "vendor": "Reflection", "model_family": "reflection-70b", "parameter_count_b": 70.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Reflection Reflection 70B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 42.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-235b-a22b-instruct-2507", "name": "Qwen3 235B A22B Instruct 2507", "vendor": "Qwen", "model_family": "qwen3-235b-a22b-instruct-2507", "parameter_count_b": 235.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3 235B A22B Instruct 2507 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 41.43, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "claude-3-5-sonnet-20241016", "name": "Claude 3.5 Sonnet (2024-10-16)", "vendor": "Anthropic", "model_family": "claude-3-5-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3.5 Sonnet (2024-10-16) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 40.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3-1", "name": "DeepSeek V3.1", "vendor": "DeepSeek", "model_family": "deepseek-v3-1", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3.1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 40.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "devstral-small-2-24b-instruct-2512", "name": "Devstral Small 2 24B Instruct 2512", "vendor": "Mistral", "model_family": "devstral-small-2-24b-instruct-2512", "parameter_count_b": 24.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Devstral Small 2 24B Instruct 2512 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 40.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-32b", "name": "Qwen3 32B", "vendor": "qwen", "model_family": "qwen3-32b", "parameter_count_b": 32.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3-32b", "card_summary": "qwen Qwen3 32B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 40.0, "input_price_per_million": 0.08, "output_price_per_million": 0.28}, {"slug": "claude-4-sonnet-high", "name": "Claude 4 Sonnet (high)", "vendor": "Anthropic", "model_family": "claude-4-sonnet", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 4 Sonnet (high) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 39.33, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen2-5-coder-3b-instruct", "name": "Qwen2.5 Coder 3B Instruct", "vendor": "Qwen", "model_family": "qwen2-5-coder-3b-instruct", "parameter_count_b": 3.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 Coder 3B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 39.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-6-35b-a3b", "name": "Qwen3.6 35B A3B", "vendor": "qwen", "model_family": "qwen3-6-35b-a3b", "parameter_count_b": 35.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3.6-35b-a3b", "card_summary": "qwen Qwen3.6 35B A3B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 38.75, "input_price_per_million": 0.09999999999999999, "output_price_per_million": 0.8999999999999999}, {"slug": "command-r-08-24", "name": "Command R (08 24)", "vendor": "Cohere", "model_family": "command-r-08-24", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Cohere Command R (08 24) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 38.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-1-5-flash", "name": "Gemini 1.5 Flash", "vendor": "Google", "model_family": "gemini-1-5-flash", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 1.5 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 38.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "mistral-small", "name": "Mistral Small", "vendor": "Meta", "model_family": "mistral-small", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Mistral Small on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 38.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-exp-1206", "name": "Gemini Exp 1206", "vendor": "Google", "model_family": "gemini-exp-1206", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini Exp 1206 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 38.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-r1-january-2025", "name": "DeepSeek R1 (January 2025)", "vendor": "DeepSeek", "model_family": "deepseek-r1-january-2025", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek R1 (January 2025) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 13, "best_success_rate": 38.11, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "devstral-small-2507", "name": "DevStral Small 2507", "vendor": "Mistral", "model_family": "devstral-small-2507", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral DevStral Small 2507 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 38.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-235b-a22b-no-thinking", "name": "Qwen3 235B A22B No Thinking", "vendor": "Qwen", "model_family": "qwen3-235b-a22b-no-thinking", "parameter_count_b": 235.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3 235B A22B No Thinking on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 37.89, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemma-4-31b-it", "name": "Gemma 4 31B IT", "vendor": "google", "model_family": "gemma-4-31b-it", "parameter_count_b": 31.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemma-4-31b-it", "card_summary": "google Gemma 4 31B IT on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 37.6, "input_price_per_million": 0.09, "output_price_per_million": 0.33999999999999997}, {"slug": "llama-3-1-8b-instruct", "name": "Llama 3.1 8b Instruct", "vendor": "meta-llama", "model_family": "llama-3-1-8b-instruct", "parameter_count_b": 8.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "meta-llama/llama-3.1-8b-instruct", "card_summary": "meta-llama Llama 3.1 8b Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 37.6, "input_price_per_million": 0.049999999999999996, "output_price_per_million": 0.08}, {"slug": "qwen1-5-110b-chat", "name": "Qwen1.5 110b Chat", "vendor": "Qwen", "model_family": "qwen1-5-110b-chat", "parameter_count_b": 110.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen1.5 110b Chat on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 37.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-4-7-flash", "name": "GLM 4.7 Flash", "vendor": "z-ai", "model_family": "glm-4-7-flash", "parameter_count_b": null, "context_length": 202752, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-4.7-flash", "card_summary": "z-ai GLM 4.7 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 36.3, "input_price_per_million": 0.06, "output_price_per_million": 0.39999999999999997}, {"slug": "gemma2-27b-instruct-q8-0", "name": "Gemma2 27b Instruct Q8 0", "vendor": "Google", "model_family": "gemma2-27b-instruct-q8-0", "parameter_count_b": 27.0, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemma2 27b Instruct Q8 0 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 36.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-2-0-pro", "name": "Gemini 2.0 Pro", "vendor": "Google", "model_family": "gemini-2-0-pro", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 2.0 Pro on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 35.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4o-mini-20240718", "name": "GPT-4o mini (2024-07-18)", "vendor": "OpenAI", "model_family": "gpt-4o-mini", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4o mini (2024-07-18) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 35.52, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-oss-120b", "name": "GPT Oss 120b", "vendor": "openai", "model_family": "gpt-oss-120b", "parameter_count_b": 120.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-oss-120b", "card_summary": "openai GPT Oss 120b on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 35.45, "input_price_per_million": 0.037, "output_price_per_million": 0.16999999999999998}, {"slug": "qwen3-235b-a22b-thinking-2507", "name": "Qwen3 235B A22B Thinking 2507", "vendor": "qwen", "model_family": "qwen3-235b-a22b-thinking-2507", "parameter_count_b": 235.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3-235b-a22b-thinking-2507", "card_summary": "qwen Qwen3 235B A22B Thinking 2507 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 35.24, "input_price_per_million": 0.22999999999999998, "output_price_per_million": 2.3}, {"slug": "gpt-5-nano-medium", "name": "GPT-5 nano (medium)", "vendor": "OpenAI", "model_family": "gpt-5-nano", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-5 nano (medium) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 34.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-3-mini-beta-low", "name": "GROK 3 Mini Beta (low)", "vendor": "xAI", "model_family": "grok-3-mini-beta-low", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 3 Mini Beta (low) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 34.7, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "codeqwen-7b-chat-v1-5-q8-0", "name": "Codeqwen 7b Chat V1.5 Q8 0", "vendor": "Qwen", "model_family": "codeqwen-7b-chat-v1-5-q8-0", "parameter_count_b": 7.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Codeqwen 7b Chat V1.5 Q8 0 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 34.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-5-397b", "name": "Qwen3.5 397B", "vendor": "Qwen", "model_family": "qwen3-5-397b", "parameter_count_b": 397.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3.5 397B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 34.5, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "openhands-versa-claude4", "name": "Openhands Versa Claude4", "vendor": "Anthropic", "model_family": "openhands-versa-claude4", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Openhands Versa Claude4 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 34.43, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "horizon-beta", "name": "Horizon Beta", "vendor": "openrouter", "model_family": "horizon-beta", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "openrouter Horizon Beta on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 34.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "glm-5-turbo", "name": "GLM 5 Turbo", "vendor": "z-ai", "model_family": "glm-5-turbo", "parameter_count_b": null, "context_length": 202752, "homepage_url": null, "hf_model_id": null, "openrouter_id": "z-ai/glm-5-turbo", "card_summary": "z-ai GLM 5 Turbo on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 33.9, "input_price_per_million": 1.2, "output_price_per_million": 4.0}, {"slug": "claude-3-7-20250219", "name": "Claude 3 7 20250219", "vendor": "Anthropic", "model_family": "claude-3-7-20250219", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3 7 20250219 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 33.83, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "mistral-nemo-12b-instruct-2407-q4-k-m", "name": "Mistral Nemo 12b Instruct 2407 Q4 K M", "vendor": "Meta", "model_family": "mistral-nemo-12b-instruct-2407-q4-k-m", "parameter_count_b": 12.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Mistral Nemo 12b Instruct 2407 Q4 K M on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 33.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-32b-thinking", "name": "Qwen3 32B Thinking", "vendor": "Qwen", "model_family": "qwen3-32b-thinking", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3 32B Thinking on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 32.63, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-coder-v2-0724-deprecated", "name": "DeepSeek Coder V2 0724 (deprecated)", "vendor": "DeepSeek", "model_family": "deepseek-coder-v2-0724-deprecated", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek Coder V2 0724 (deprecated) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 32.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4o-20240612", "name": "GPT-4o (2024-06-12)", "vendor": "OpenAI", "model_family": "gpt-4o", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4o (2024-06-12) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 32.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-1-mini", "name": "GPT-4.1 mini", "vendor": "openai", "model_family": "gpt-4-1-mini", "parameter_count_b": null, "context_length": 1047576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-4.1-mini", "card_summary": "openai GPT-4.1 mini on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 32.4, "input_price_per_million": 0.39999999999999997, "output_price_per_million": 1.5999999999999999}, {"slug": "codegeex4", "name": "Codegeex4", "vendor": "Meta", "model_family": "codegeex4", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Codegeex4 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 32.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-next-80b-a3b-instruct", "name": "Qwen3 Next 80B A3B Instruct", "vendor": "qwen", "model_family": "qwen3-next-80b-a3b-instruct", "parameter_count_b": 80.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3-next-80b-a3b-instruct", "card_summary": "qwen Qwen3 Next 80B A3B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 31.76, "input_price_per_million": 0.09999999999999999, "output_price_per_million": 1.1}, {"slug": "command-r-plus", "name": "Command R Plus", "vendor": "Cohere", "model_family": "command-r-plus", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Cohere Command R Plus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 31.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen2-5-coder-1-5b-instruct", "name": "Qwen2.5 Coder 1.5B Instruct", "vendor": "Qwen", "model_family": "qwen2-5-coder-1-5b-instruct", "parameter_count_b": 5.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 Coder 1.5B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 31.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-chat-v2-5", "name": "DeepSeek Chat V2.5", "vendor": "DeepSeek", "model_family": "deepseek-chat-v2-5", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek Chat V2.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 31.5, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "mimo-v2-flash", "name": "MiMo V2 Flash", "vendor": "Xiaomi", "model_family": "mimo-v2-flash", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Xiaomi MiMo V2 Flash on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 30.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-32b-no-thinking", "name": "Qwen3 32B No Thinking", "vendor": "Qwen", "model_family": "qwen3-32b-no-thinking", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3 32B No Thinking on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 30.53, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "hermes3-8b-llama3-1", "name": "Hermes3 8b Llama3.1", "vendor": "Meta", "model_family": "hermes3-8b-llama3-1", "parameter_count_b": 8.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Hermes3 8b Llama3.1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 30.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "horizon-alpha", "name": "Horizon Alpha", "vendor": "openrouter", "model_family": "horizon-alpha", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "openrouter Horizon Alpha on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 30.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "sonnet-20241022", "name": "Sonnet 20241022", "vendor": "Anthropic", "model_family": "sonnet-20241022", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Sonnet 20241022 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 30.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "lingma-swe-gpt-72b-v0925", "name": "Lingma SWE GPT 72b (v0925)", "vendor": "OpenAI", "model_family": "lingma-swe-gpt-72b-v0925", "parameter_count_b": 72.0, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI Lingma SWE GPT 72b (v0925) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 28.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gemini-2-5-flash-20250417", "name": "Gemini 2.5 Flash (2025-04-17)", "vendor": "Google", "model_family": "gemini-2-5-flash", "parameter_count_b": null, "context_length": 1000000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Google Gemini 2.5 Flash (2025-04-17) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 28.73, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-235b-a22b-thinking", "name": "Qwen3 235B A22B Thinking", "vendor": "Qwen", "model_family": "qwen3-235b-a22b-thinking", "parameter_count_b": 235.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen3 235B A22B Thinking on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 28.42, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "chatgpt-4o-20250215", "name": "ChatGPT-4o (2025-02-15)", "vendor": "OpenAI", "model_family": "chatgpt-4o", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI ChatGPT-4o (2025-02-15) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 27.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama3-2-3b-instruct", "name": "Llama3.2 3b Instruct", "vendor": "Meta", "model_family": "llama3-2-3b-instruct", "parameter_count_b": 3.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama3.2 3b Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 26.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "tulu3", "name": "Tulu3", "vendor": "Meta", "model_family": "tulu3", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Tulu3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 26.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "lingma-swe-gpt-72b-v0918", "name": "Lingma SWE GPT 72b (v0918)", "vendor": "OpenAI", "model_family": "lingma-swe-gpt-72b-v0918", "parameter_count_b": 72.0, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI Lingma SWE GPT 72b (v0918) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 25.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-1-mini-20250414", "name": "GPT-4.1 mini (2025-04-14)", "vendor": "OpenAI", "model_family": "gpt-4-1-mini", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4.1 mini (2025-04-14) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 23.94, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "hermes3", "name": "Hermes3", "vendor": "Meta", "model_family": "hermes3", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Hermes3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 22.6, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama-4-maverick-17b-128e-instruct", "name": "Llama 4 Maverick 17B 128E Instruct", "vendor": "Meta", "model_family": "llama-4-maverick-17b-128e-instruct", "parameter_count_b": 17.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama 4 Maverick 17B 128E Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 22.5, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen-max-2025-01-25", "name": "QWEN Max 2025 01 25", "vendor": "Qwen", "model_family": "qwen-max-2025-01-25", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen QWEN Max 2025 01 25 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 21.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen2-5-72b-instruct", "name": "Qwen2.5 72B Instruct", "vendor": "qwen", "model_family": "qwen2-5-72b-instruct", "parameter_count_b": 72.0, "context_length": 32768, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen-2.5-72b-instruct", "card_summary": "qwen Qwen2.5 72B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 21.05, "input_price_per_million": 0.36, "output_price_per_million": 0.39999999999999997}, {"slug": "llama-4-maverick-instruct", "name": "Llama 4 Maverick Instruct", "vendor": "Meta", "model_family": "llama-4-maverick-instruct", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama 4 Maverick Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 21.04, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwq-32b", "name": "QwQ 32B", "vendor": "Qwen", "model_family": "qwq-32b", "parameter_count_b": 32.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen QwQ 32B on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 20.9, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "granite3-dense-8b", "name": "Granite3 Dense 8b", "vendor": "Meta", "model_family": "granite3-dense-8b", "parameter_count_b": 8.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Granite3 Dense 8b on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 20.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "deepseek-v3-1-august-2025", "name": "DeepSeek V3.1 (August 2025)", "vendor": "DeepSeek", "model_family": "deepseek-v3-1-august-2025", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3.1 (August 2025) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 20.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "grok-4-20-beta", "name": "GROK 4.20 Beta", "vendor": "xAI", "model_family": "grok-4-20-beta", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "xAI GROK 4.20 Beta on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 19.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-30b-a3b-thinking-2507", "name": "Qwen3 30B A3B Thinking 2507", "vendor": "qwen", "model_family": "qwen3-30b-a3b-thinking-2507", "parameter_count_b": 30.0, "context_length": 81920, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3-30b-a3b-thinking-2507", "card_summary": "qwen Qwen3 30B A3B Thinking 2507 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 19.05, "input_price_per_million": 0.19999999999999998, "output_price_per_million": 2.4}, {"slug": "llama-4-scout-17b-16e-instruct", "name": "Llama 4 Scout 17B 16E Instruct", "vendor": "Meta", "model_family": "llama-4-scout-17b-16e-instruct", "parameter_count_b": 17.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama 4 Scout 17B 16E Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 18.75, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "lingma-swe-gpt-7b-v0925", "name": "Lingma SWE GPT 7b (v0925)", "vendor": "OpenAI", "model_family": "lingma-swe-gpt-7b-v0925", "parameter_count_b": 7.0, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI Lingma SWE GPT 7b (v0925) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 18.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "qwen3-30b-a3b-instruct-2507", "name": "Qwen3 30B A3B Instruct 2507", "vendor": "qwen", "model_family": "qwen3-30b-a3b-instruct-2507", "parameter_count_b": 30.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "qwen/qwen3-30b-a3b-instruct-2507", "card_summary": "qwen Qwen3 30B A3B Instruct 2507 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 17.14, "input_price_per_million": 0.04815, "output_price_per_million": 0.19305}, {"slug": "claude-3-opus", "name": "Claude 3 Opus", "vendor": "Anthropic", "model_family": "claude-3-opus", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Anthropic Claude 3 Opus on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 15.8, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama-4-maverick", "name": "Llama 4 Maverick", "vendor": "meta-llama", "model_family": "llama-4-maverick", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "meta-llama/llama-4-maverick", "card_summary": "meta-llama Llama 4 Maverick on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 15.6, "input_price_per_million": 0.19999999999999998, "output_price_per_million": 0.7999999999999999}, {"slug": "qwen2-5-coder-0-5b-instruct", "name": "Qwen2.5 Coder 0.5B Instruct", "vendor": "Qwen", "model_family": "qwen2-5-coder-0-5b-instruct", "parameter_count_b": 5.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Qwen Qwen2.5 Coder 0.5B Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 14.3, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-oss-20b", "name": "GPT Oss 20b", "vendor": "openai", "model_family": "gpt-oss-20b", "parameter_count_b": 20.0, "context_length": 131072, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-oss-20b", "card_summary": "openai GPT Oss 20b on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 14.29, "input_price_per_million": 0.03, "output_price_per_million": 0.13}, {"slug": "gemma-3-27b-it", "name": "Gemma 3 27b It", "vendor": "google", "model_family": "gemma-3-27b-it", "parameter_count_b": 27.0, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "google/gemma-3-27b-it", "card_summary": "google Gemma 3 27b It on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 13.68, "input_price_per_million": 0.08, "output_price_per_million": 0.44999999999999996}, {"slug": "command-a-03-2025-quality", "name": "Command A 03 2025 Quality", "vendor": "Cohere", "model_family": "command-a-03-2025-quality", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Cohere Command A 03 2025 Quality on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 12.0, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-oss-120b-august-2025", "name": "GPT OSS 120B (August 2025)", "vendor": "OpenAI", "model_family": "gpt-oss-120b-august-2025", "parameter_count_b": 120.0, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT OSS 120B (August 2025) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 11.11, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-oss-120b-high-august-2025", "name": "GPT OSS 120B High (August 2025)", "vendor": "OpenAI", "model_family": "gpt-oss-120b-high-august-2025", "parameter_count_b": 120.0, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT OSS 120B High (August 2025) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 11.11, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "codestral-25-01", "name": "Codestral 25.01", "vendor": "Mistral", "model_family": "codestral-25-01", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Mistral Codestral 25.01 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 11.1, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "lingma-swe-gpt-7b-v0918", "name": "Lingma SWE GPT 7b (v0918)", "vendor": "OpenAI", "model_family": "lingma-swe-gpt-7b-v0918", "parameter_count_b": 7.0, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI Lingma SWE GPT 7b (v0918) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 10.2, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama-4-scout-instruct", "name": "Llama 4 Scout Instruct", "vendor": "Meta", "model_family": "llama-4-scout-instruct", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama 4 Scout Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 2, "best_success_rate": 9.06, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-1-nano", "name": "GPT-4.1 nano", "vendor": "openai", "model_family": "gpt-4-1-nano", "parameter_count_b": null, "context_length": 1047576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/gpt-4.1-nano", "card_summary": "openai GPT-4.1 nano on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 8.9, "input_price_per_million": 0.09999999999999999, "output_price_per_million": 0.39999999999999997}, {"slug": "deepseek-r1-may-2025", "name": "DeepSeek R1 (May 2025)", "vendor": "DeepSeek", "model_family": "deepseek-r1-may-2025", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek R1 (May 2025) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 8.89, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "llama-3-1-405b-instruct", "name": "Llama 3.1 405b Instruct", "vendor": "Meta", "model_family": "llama-3-1-405b-instruct", "parameter_count_b": 405.0, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "Meta Llama 3.1 405b Instruct on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 3.33, "input_price_per_million": null, "output_price_per_million": null}, {"slug": "gpt-4-1-nano-20250414", "name": "GPT-4.1 nano (2025-04-14)", "vendor": "OpenAI", "model_family": "gpt-4-1-nano", "parameter_count_b": null, "context_length": 400000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "OpenAI GPT-4.1 nano (2025-04-14) on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 1, "best_success_rate": 1.25, "input_price_per_million": null, "output_price_per_million": null}]