{"benchmark": {"slug": "swe-rebench", "name": "SWE-rebench", "description": "Continuous SWE-rebench leaderboard with rolling task windows.", "category": "eval", "split": null, "language": "python", "task_count": null, "homepage_url": "https://swe-rebench.com/", "paper_url": null, "hf_dataset_id": null, "official_leaderboard_url": "https://swe-rebench.com/", "is_public_leaderboard": true, "harness_count": 5, "model_count": 107, "score_count": 110, "best_success_rate": 100.0}, "protocol": {"eval_protocol": "SWE-rebench resolved rate (best rolling window)", "temperature": null, "max_turns": null, "context_budget_tokens": null, "n": 110}, "rankings": {"benchmark": {"slug": "swe-rebench", "name": "SWE-rebench", "description": "Continuous SWE-rebench leaderboard with rolling task windows.", "category": "eval", "split": null, "language": "python", "task_count": null, "homepage_url": "https://swe-rebench.com/", "paper_url": null, "hf_dataset_id": null, "official_leaderboard_url": "https://swe-rebench.com/", "is_public_leaderboard": true, "harness_count": null, "model_count": null, "score_count": null, "best_success_rate": null}, "sort": "success_rate", "rows": [{"rank": 1, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-5-opus-high", "name": "Claude 5 Opus (high)", "vendor": "Anthropic"}, "success_rate": 100.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 2, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "swe-rebench-agent-product", "name": "SWE-rebench agent (product)", "vendor": null}, "success_rate": 84.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 3, "harness": {"slug": "junie", "name": "Junie", "vendor": "jetbrains", "scaffold_code": null, "repo_url": null, "homepage_url": "https://swe-rebench.com/", "openrouter_icon_url": "https://www.jetbrains.com/junie", "leaderboard_icon_url": null}, "model": {"slug": "swe-rebench-agent-product", "name": "SWE-rebench agent (product)", "vendor": null}, "success_rate": 84.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 4, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "fable-5-[high]", "name": "Fable 5 [high]", "vendor": "Anthropic"}, "success_rate": 84.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 5, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "glm-5-2-[high]", "name": "GLM 5.2 [high]", "vendor": "Zhipu"}, "success_rate": 80.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 6, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-5-sonnet-high", "name": "Claude 5 Sonnet (high)", "vendor": "Anthropic"}, "success_rate": 80.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 7, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "grok-4-5-[high]", "name": "GROK 4.5 [high]", "vendor": "xAI"}, "success_rate": 76.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 8, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-6-medium", "name": "GPT-5.6 (medium)", "vendor": "OpenAI"}, "success_rate": 75.29, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 9, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "swe-rebench-agent-product", "name": "SWE-rebench agent (product)", "vendor": null}, "success_rate": 72.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 10, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-2-medium", "name": "GPT-5.2 (medium)", "vendor": "OpenAI"}, "success_rate": 71.33, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 11, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-5-xhigh", "name": "GPT-5.5 (xhigh)", "vendor": "OpenAI"}, "success_rate": 71.11, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 12, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-4-medium", "name": "GPT-5.4 (medium)", "vendor": "OpenAI"}, "success_rate": 70.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 13, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-4-5-opus", "name": "Claude 4.5 Opus", "vendor": "Anthropic"}, "success_rate": 68.89, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 14, "harness": {"slug": "cursor-cli", "name": "Cursor CLI", "vendor": "Cursor", "scaffold_code": null, "repo_url": "https://github.com/getcursor/cursor", "homepage_url": "https://cursor.com", "openrouter_icon_url": "https://cursor.com/apple-touch-icon.png", "leaderboard_icon_url": null}, "model": {"slug": "swe-rebench-agent-product", "name": "SWE-rebench agent (product)", "vendor": null}, "success_rate": 68.24, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 15, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-5-medium", "name": "GPT-5.5 (medium)", "vendor": "OpenAI"}, "success_rate": 67.78, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 16, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-4-6-opus-high", "name": "Claude 4.6 Opus (high)", "vendor": "Anthropic"}, "success_rate": 67.33, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 17, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-2-xhigh", "name": "GPT-5.2 (xhigh)", "vendor": "OpenAI"}, "success_rate": 67.32, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 18, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemini-3-pro-preview", "name": "Gemini 3 Pro Preview", "vendor": "Google"}, "success_rate": 67.27, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 19, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "minimax-m3", "name": "MiniMax M3", "vendor": "minimax"}, "success_rate": 67.06, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 20, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-4-7-opus-high", "name": "Claude 4.7 Opus (high)", "vendor": "Anthropic"}, "success_rate": 66.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 21, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-2025-medium", "name": "GPT-5.2025 (medium)", "vendor": "OpenAI"}, "success_rate": 66.36, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 22, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-4-8-opus-xhigh", "name": "Claude 4.8 Opus (xhigh)", "vendor": "Anthropic"}, "success_rate": 65.56, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 23, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-1-codex-max", "name": "GPT-5.1 codex (max)", "vendor": "openai"}, "success_rate": 65.45, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 24, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemini-3-1-pro-preview", "name": "Gemini 3.1 Pro Preview", "vendor": "google"}, "success_rate": 64.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 25, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-4-sonnet", "name": "Claude 4 Sonnet", "vendor": "Anthropic"}, "success_rate": 64.21, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 26, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "deepseek-v3-2", "name": "DeepSeek V3.2", "vendor": "deepseek"}, "success_rate": 64.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 27, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-3-codex", "name": "GPT-5.3 codex", "vendor": "openai"}, "success_rate": 64.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 28, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-4-5-sonnet", "name": "Claude 4.5 Sonnet", "vendor": "Anthropic"}, "success_rate": 63.64, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 29, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemini-3-flash-preview", "name": "Gemini 3 Flash Preview", "vendor": "google"}, "success_rate": 63.33, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 30, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "success_rate": 62.96, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 31, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-3-codex-xhigh", "name": "GPT-5.3 codex (xhigh)", "vendor": "OpenAI"}, "success_rate": 62.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 32, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-5-397b-a17b", "name": "Qwen3.5 397B A17B", "vendor": "qwen"}, "success_rate": 62.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 33, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-5-27b", "name": "Qwen3.5 27B", "vendor": "qwen"}, "success_rate": 62.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 34, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemini-3-5-flash", "name": "Gemini 3.5 Flash", "vendor": "google"}, "success_rate": 62.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 35, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-2-codex", "name": "GPT-5.2 codex", "vendor": "openai"}, "success_rate": 62.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 36, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "step-3-5-flash", "name": "Step 3.5 Flash", "vendor": "stepfun"}, "success_rate": 62.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 37, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "mimo-v2-5-pro", "name": "MiMo V2.5 Pro", "vendor": "xiaomi"}, "success_rate": 61.54, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 38, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-2025-high", "name": "GPT-5.2025 (high)", "vendor": "OpenAI"}, "success_rate": 61.43, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 39, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "success_rate": 61.33, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 40, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-4-6-sonnet", "name": "Claude 4.6 Sonnet", "vendor": "Anthropic"}, "success_rate": 61.33, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 41, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-codex", "name": "GPT-5 codex", "vendor": "OpenAI"}, "success_rate": 60.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 42, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-1-codex", "name": "GPT-5.1 codex", "vendor": "openai"}, "success_rate": 60.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 43, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "glm-4-7", "name": "GLM 4.7", "vendor": "z-ai"}, "success_rate": 60.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 44, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "kimi-k2-thinking", "name": "KIMI K2 Thinking", "vendor": "moonshotai"}, "success_rate": 58.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 45, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "glm-5-1", "name": "GLM 5 1", "vendor": "Zhipu"}, "success_rate": 58.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 46, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-5-35b-a3b", "name": "Qwen3.5 35B A3B", "vendor": "qwen"}, "success_rate": 56.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 47, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "o3", "name": "o3", "vendor": "openai"}, "success_rate": 56.36, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 48, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-4-1-opus", "name": "Claude 4.1 Opus", "vendor": "Anthropic"}, "success_rate": 56.36, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 49, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-coder-next", "name": "Qwen3 Coder Next", "vendor": "qwen"}, "success_rate": 55.33, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 50, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "minimax-m2-5", "name": "MiniMax M2.5", "vendor": "minimax"}, "success_rate": 54.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 51, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "success_rate": 54.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 52, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-mini-medium", "name": "GPT-5 mini (medium)", "vendor": "OpenAI"}, "success_rate": 54.29, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 53, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "kimi-k2-instruct-0905", "name": "KIMI K2 Instruct 0905", "vendor": "Moonshot"}, "success_rate": 54.29, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 54, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "minimax-m2-7", "name": "MiniMax M2.7", "vendor": "minimax"}, "success_rate": 54.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 55, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "devstral-2-123b-instruct-2512", "name": "Devstral 2 123B Instruct 2512", "vendor": "Mistral"}, "success_rate": 52.73, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 56, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-4-1-20250414", "name": "GPT-4.1 (2025-04-14)", "vendor": "OpenAI"}, "success_rate": 51.58, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 57, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "glm-4-5", "name": "GLM 4.5", "vendor": "z-ai"}, "success_rate": 51.43, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 58, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-coder-480b-a35b-instruct", "name": "Qwen3 Coder 480B A35B Instruct", "vendor": "Qwen"}, "success_rate": 50.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 59, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "grok-4", "name": "GROK 4", "vendor": "xAI"}, "success_rate": 50.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 60, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "glm-4-6", "name": "GLM 4.6", "vendor": "z-ai"}, "success_rate": 49.6, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 61, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "deepseek-v4-pro-[high]", "name": "DeepSeek V4 Pro [high]", "vendor": "DeepSeek"}, "success_rate": 48.97, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 62, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "grok-code-fast-1", "name": "GROK Code Fast 1", "vendor": "xAI"}, "success_rate": 48.57, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 63, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "deepseek-v3-0324", "name": "DeepSeek V3 0324", "vendor": "DeepSeek"}, "success_rate": 48.42, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 64, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "minimax-m2-1", "name": "MiniMax M2.1", "vendor": "minimax"}, "success_rate": 48.18, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 65, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "glm-4-5-air", "name": "GLM 4.5 Air", "vendor": "z-ai"}, "success_rate": 47.91, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 66, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-oss-120b-high", "name": "GPT Oss 120b High", "vendor": "OpenAI"}, "success_rate": 46.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 67, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemma-4-31b", "name": "Gemma 4 31B", "vendor": "Google"}, "success_rate": 46.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 68, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-mini-high", "name": "GPT-5 mini (high)", "vendor": "OpenAI"}, "success_rate": 46.3, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 69, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "claude-3-5-sonnet", "name": "Claude 3.5 Sonnet", "vendor": "Anthropic"}, "success_rate": 44.21, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 70, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "minimax-m2", "name": "MiniMax M2", "vendor": "minimax"}, "success_rate": 43.81, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 71, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "o4-mini", "name": "o4 mini", "vendor": "openai"}, "success_rate": 43.64, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 72, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "deepseek-v4-flash-[high]", "name": "DeepSeek V4 Flash [high]", "vendor": "DeepSeek"}, "success_rate": 43.2, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 73, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek"}, "success_rate": 43.16, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 74, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-5-2025", "name": "GPT-5.2025", "vendor": "OpenAI"}, "success_rate": 42.86, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 75, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-6-27b", "name": "Qwen3.6 27B", "vendor": "qwen"}, "success_rate": 41.67, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 76, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-235b-a22b-instruct-2507", "name": "Qwen3 235B A22B Instruct 2507", "vendor": "Qwen"}, "success_rate": 41.43, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 77, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "kimi-k2", "name": "KIMI K2", "vendor": "moonshotai"}, "success_rate": 40.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 78, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "deepseek-v3-1", "name": "DeepSeek V3.1", "vendor": "DeepSeek"}, "success_rate": 40.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 79, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "devstral-small-2-24b-instruct-2512", "name": "Devstral Small 2 24B Instruct 2512", "vendor": "Mistral"}, "success_rate": 40.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 80, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-6-35b-a3b", "name": "Qwen3.6 35B A3B", "vendor": "qwen"}, "success_rate": 38.75, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 81, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-235b-a22b-no-thinking", "name": "Qwen3 235B A22B No Thinking", "vendor": "Qwen"}, "success_rate": 37.89, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 82, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "glm-4-7-flash", "name": "GLM 4.7 Flash", "vendor": "z-ai"}, "success_rate": 36.3, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 83, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemini-2-5-flash", "name": "Gemini 2.5 Flash", "vendor": "google"}, "success_rate": 35.71, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 84, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-oss-120b", "name": "GPT Oss 120b", "vendor": "openai"}, "success_rate": 35.45, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 85, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-235b-a22b-thinking-2507", "name": "Qwen3 235B A22B Thinking 2507", "vendor": "qwen"}, "success_rate": 35.24, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 86, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-coder-30b-a3b-instruct", "name": "Qwen3 Coder 30B A3B Instruct", "vendor": "qwen"}, "success_rate": 34.29, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 87, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "horizon-beta", "name": "Horizon Beta", "vendor": "openrouter"}, "success_rate": 34.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 88, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "llama-3-3-70b-instruct", "name": "Llama 3.3 70B Instruct", "vendor": "meta-llama"}, "success_rate": 33.68, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 89, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemini-2-5-flash-preview", "name": "Gemini 2.5 Flash Preview", "vendor": "Google"}, "success_rate": 33.68, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 90, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemini-2-5-pro", "name": "Gemini 2.5 Pro", "vendor": "google"}, "success_rate": 33.33, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 91, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-32b-thinking", "name": "Qwen3 32B Thinking", "vendor": "Qwen"}, "success_rate": 32.63, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 92, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "devstral-small-2505", "name": "Devstral Small 2505", "vendor": "Mistral"}, "success_rate": 32.63, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 93, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-next-80b-a3b-instruct", "name": "Qwen3 Next 80B A3B Instruct", "vendor": "qwen"}, "success_rate": 31.76, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 94, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "deepseek-r1-0528", "name": "DeepSeek R1 0528", "vendor": "deepseek"}, "success_rate": 31.43, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 95, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-32b-no-thinking", "name": "Qwen3 32B No Thinking", "vendor": "Qwen"}, "success_rate": 30.53, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 96, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "horizon-alpha", "name": "Horizon Alpha", "vendor": "openrouter"}, "success_rate": 30.0, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 97, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-235b-a22b-thinking", "name": "Qwen3 235B A22B Thinking", "vendor": "Qwen"}, "success_rate": 28.42, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 98, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemini-2-0-flash", "name": "Gemini 2.0 Flash", "vendor": "Google"}, "success_rate": 24.29, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 99, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-4-1-mini-20250414", "name": "GPT-4.1 mini (2025-04-14)", "vendor": "OpenAI"}, "success_rate": 23.81, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 100, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "llama-4-maverick-17b-128e-instruct", "name": "Llama 4 Maverick 17B 128E Instruct", "vendor": "Meta"}, "success_rate": 22.5, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 101, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen2-5-72b-instruct", "name": "Qwen2.5 72B Instruct", "vendor": "qwen"}, "success_rate": 21.05, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 102, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-235b-a22b", "name": "Qwen3 235B A22B", "vendor": "qwen"}, "success_rate": 19.47, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 103, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-30b-a3b-thinking-2507", "name": "Qwen3 30B A3B Thinking 2507", "vendor": "qwen"}, "success_rate": 19.05, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 104, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "llama-4-scout-17b-16e-instruct", "name": "Llama 4 Scout 17B 16E Instruct", "vendor": "Meta"}, "success_rate": 18.75, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 105, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-30b-a3b-instruct-2507", "name": "Qwen3 30B A3B Instruct 2507", "vendor": "qwen"}, "success_rate": 17.14, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 106, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-oss-20b", "name": "GPT Oss 20b", "vendor": "openai"}, "success_rate": 14.29, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 107, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gemma-3-27b-it", "name": "Gemma 3 27b It", "vendor": "google"}, "success_rate": 13.68, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 108, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen3-32b", "name": "Qwen3 32B", "vendor": "qwen"}, "success_rate": 8.57, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 109, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "qwen2-5-coder-32b-instruct", "name": "Qwen2.5 Coder 32B Instruct", "vendor": "qwen"}, "success_rate": 7.62, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}, {"rank": 110, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "scaffold_code": null, "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "homepage_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/mini-icon.svg"}, "model": {"slug": "gpt-4-1-nano-20250414", "name": "GPT-4.1 nano (2025-04-14)", "vendor": "OpenAI"}, "success_rate": 1.25, "resolved_count": null, "total_count": null, "cost_usd": null, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null}]}}