{"model": {"slug": "o1", "name": "o1", "vendor": "openai", "model_family": "o1", "parameter_count_b": null, "context_length": 200000, "homepage_url": null, "hf_model_id": null, "openrouter_id": "openai/o1", "card_summary": "openai o1 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 90.25, "input_price_per_million": 15.0, "output_price_per_million": 60.0}, "scores": [{"success_rate": 90.25, "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, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "HAL reliability composite (mean of 4 dimension aggregates)", "source": "hal_reliability_site", "source_url": "https://hal.cs.princeton.edu/reliability/benchmark/taubench_airline/", "observed_at": null, "harness": {"slug": "hal-generalist-agent", "name": "HAL Generalist Agent", "vendor": "Princeton PLI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o1", "name": "o1", "vendor": "openai"}, "benchmark": {"slug": "hal-reliability-tau-bench-airline", "name": "HAL Reliability \u2014 \u03c4-bench Airline (clean)"}}, {"success_rate": 87.75, "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, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "HAL reliability composite (mean of 4 dimension aggregates)", "source": "hal_reliability_site", "source_url": "https://hal.cs.princeton.edu/reliability/benchmark/gaia/", "observed_at": null, "harness": {"slug": "hal-generalist-agent", "name": "HAL Generalist Agent", "vendor": "Princeton PLI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o1", "name": "o1", "vendor": "openai"}, "benchmark": {"slug": "hal-reliability-gaia", "name": "HAL Reliability \u2014 GAIA"}}, {"success_rate": 86.0, "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, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "HAL reliability composite (mean of 4 dimension aggregates)", "source": "hal_reliability_site", "source_url": "https://hal.cs.princeton.edu/reliability/benchmark/taubench_airline_original/", "observed_at": null, "harness": {"slug": "hal-generalist-agent", "name": "HAL Generalist Agent", "vendor": "Princeton PLI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o1", "name": "o1", "vendor": "openai"}, "benchmark": {"slug": "hal-reliability-tau-bench-airline-original", "name": "HAL Reliability \u2014 \u03c4-bench Airline (original)"}}, {"success_rate": 84.2, "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, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Aider edit leaderboard", "source": "aider_leaderboard", "source_url": "https://aider.chat/docs/leaderboards/", "observed_at": "2024-12-18T00:00:00+00:00", "harness": {"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o1", "name": "o1", "vendor": "openai"}, "benchmark": {"slug": "aider-edit", "name": "Aider Edit"}}, {"success_rate": 64.6, "resolved_count": 323, "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://wandb.ai", "observed_at": "2025-01-17T00:00:00+00:00", "harness": {"slug": "w&b-programmer-o1-crosscheck5", "name": "W&b Programmer O1 Crosscheck5", "vendor": "Weights & Biases", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "o1", "name": "o1", "vendor": "openai"}, "benchmark": {"slug": "swe-bench-verified", "name": "SWE-bench Verified"}}], "harnesses": [{"slug": "aider", "name": "Aider", "vendor": "Aider", "repo_url": "https://github.com/Aider-AI/aider", "openrouter_icon_url": "https://aider.chat/favicon.ico"}, {"slug": "hal-generalist-agent", "name": "HAL Generalist Agent", "vendor": "Princeton PLI", "repo_url": "https://github.com/princeton-pli/hal-harness", "openrouter_icon_url": null}, {"slug": "w&b-programmer-o1-crosscheck5", "name": "W&b Programmer O1 Crosscheck5", "vendor": "Weights & Biases", "repo_url": "https://github.com/wandb/wandb", "openrouter_icon_url": null}]}