{"model": {"slug": "o3-mini", "name": "o3 mini", "vendor": "openai", "model_family": "o3", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/o3-mini", "card_summary": "openai o3 mini on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 75.36, "input_price_per_million": 1.1, "output_price_per_million": 4.4}, "scores": [{"success_rate": 75.36, "resolved_count": null, "total_count": 1055, "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": "LiveCodeBench generation pass@1 mean", "source": "livecodebench", "source_url": "https://livecodebench.github.io/leaderboard.html", "observed_at": null, "harness": {"slug": "livecodebench", "name": "Livecodebench", "vendor": "LiveCodeBench", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o3-mini", "name": "o3 mini", "vendor": "openai"}, "benchmark": {"slug": "livecodebench-generation", "name": "LiveCodeBench (code generation)"}}, {"success_rate": 53.8, "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": "2025-01-31T00:00:00+00:00", "harness": {"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o3-mini", "name": "o3 mini", "vendor": "openai"}, "benchmark": {"slug": "aider-polyglot", "name": "Aider Polyglot"}}, {"success_rate": 42.4, "resolved_count": 212, "total_count": 500, "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": "SWE-bench Verified public submission", "source": "swe_bench_site", "source_url": "https://github.com/sorendunn/Agentless-Lite", "observed_at": "2025-02-14T00:00:00+00:00", "harness": {"slug": "agentless-lite", "name": "Agentless Lite", "vendor": "OpenAutoCoder", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o3-mini", "name": "o3 mini", "vendor": "openai"}, "benchmark": {"slug": "swe-bench-verified", "name": "SWE-bench Verified"}}, {"success_rate": 32.33, "resolved_count": 97, "total_count": 300, "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": "SWE-bench Lite public submission", "source": "swe_bench_site", "source_url": "https://github.com/sorendunn/Agentless-Lite", "observed_at": "2025-02-14T00:00:00+00:00", "harness": {"slug": "agentless-lite", "name": "Agentless Lite", "vendor": "OpenAutoCoder", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o3-mini", "name": "o3 mini", "vendor": "openai"}, "benchmark": {"slug": "swe-bench-lite", "name": "SWE-bench Lite"}}, {"success_rate": 30.33, "resolved_count": 91, "total_count": 300, "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": "SWE-bench Lite public submission", "source": "swe_bench_site", "source_url": "https://github.com/evandiewald/aegis", "observed_at": "2025-02-07T00:00:00+00:00", "harness": {"slug": "aegis-o3-mini-1-0", "name": "Aegis O3 Mini 1.0", "vendor": "Evandiewald", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o3-mini", "name": "o3 mini", "vendor": "openai"}, "benchmark": {"slug": "swe-bench-lite", "name": "SWE-bench Lite"}}], "harnesses": [{"slug": "aegis-o3-mini-1-0", "name": "Aegis O3 Mini 1.0", "vendor": "Evandiewald", "repo_url": "https://github.com/evandiewald/aegis", "openrouter_icon_url": null}, {"slug": "agentless-lite", "name": "Agentless Lite", "vendor": "OpenAutoCoder", "repo_url": "https://github.com/OpenAutoCoder/Agentless", "openrouter_icon_url": null}, {"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": "https://github.com/Aider-AI/aider", "openrouter_icon_url": "https://aider.chat/favicon.ico"}, {"slug": "livecodebench", "name": "Livecodebench", "vendor": "LiveCodeBench", "repo_url": "https://github.com/LiveCodeBench/LiveCodeBench", "openrouter_icon_url": null}]}