{"model": {"slug": "deepseek-r1", "name": "Deepseek R1", "vendor": "deepseek", "model_family": "deepseek-r1", "parameter_count_b": null, "context_length": 64000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "deepseek/deepseek-r1", "card_summary": "deepseek Deepseek R1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 3, "best_success_rate": 56.9, "input_price_per_million": 0.7, "output_price_per_million": 2.5}, "scores": [{"success_rate": 56.9, "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, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Aider polyglot leaderboard", "source": "aider_leaderboard", "source_url": "https://aider.chat/docs/leaderboards/", "observed_at": "2025-01-20T00:00:00+00:00", "harness": {"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-r1", "name": "Deepseek R1", "vendor": "deepseek"}, "benchmark": {"slug": "aider-polyglot", "name": "Aider Polyglot"}}, {"success_rate": 36.44, "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, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "MLE-bench All split any_medal_percentage", "source": "mle_bench_site", "source_url": "https://github.com/openai/mle-bench", "observed_at": "2025-09-12T00:00:00+00:00", "harness": {"slug": "internagent", "name": "InternAgent", "vendor": "Alpha Innovator", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-r1", "name": "Deepseek R1", "vendor": "deepseek"}, "benchmark": {"slug": "mle-bench", "name": "MLE-bench"}}, {"success_rate": 29.33, "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, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "MLE-bench All split any_medal_percentage", "source": "mle_bench_site", "source_url": "https://github.com/openai/mle-bench", "observed_at": "2025-06-17T00:00:00+00:00", "harness": {"slug": "ml-master", "name": "ML Master", "vendor": "Zeroxleo", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-r1", "name": "Deepseek R1", "vendor": "deepseek"}, "benchmark": {"slug": "mle-bench", "name": "MLE-bench"}}], "harnesses": [{"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": "https://github.com/Aider-AI/aider", "openrouter_icon_url": "https://aider.chat/favicon.ico"}, {"slug": "internagent", "name": "InternAgent", "vendor": "Alpha Innovator", "repo_url": "https://github.com/Alpha-Innovator/InternAgent/", "openrouter_icon_url": null}, {"slug": "ml-master", "name": "ML Master", "vendor": "Zeroxleo", "repo_url": "https://github.com/zeroxleo/ML-Master", "openrouter_icon_url": null}]}