{"benchmark": {"slug": "commit0", "name": "Commit0", "description": "Commit0 evaluates agents building new libraries from scratch (54\u201357 libs). OpenHands Index publishes SDK runs (`openhands_index`). Historical leaderboards also appear on commit-0.github.io.\n\nGreenfield category \u2014 scores are not comparable to issue-resolution % on Verified without context.", "category": "eval", "split": null, "language": null, "task_count": null, "homepage_url": "https://commit-0.github.io/", "paper_url": null, "hf_dataset_id": null, "official_leaderboard_url": "https://index.openhands.dev/", "is_public_leaderboard": true, "harness_count": 1, "model_count": 33, "score_count": 33, "best_success_rate": 62.5}, "protocol": {"eval_protocol": "OpenHands SDK v1.8.3", "temperature": null, "max_turns": null, "context_budget_tokens": null, "n": 12}, "rankings": {"benchmark": {"slug": "commit0", "name": "Commit0", "description": "Commit0 evaluates agents building new libraries from scratch (54\u201357 libs). OpenHands Index publishes SDK runs (`openhands_index`). Historical leaderboards also appear on commit-0.github.io.\n\nGreenfield category \u2014 scores are not comparable to issue-resolution % on Verified without context.", "category": "eval", "split": null, "language": null, "task_count": null, "homepage_url": "https://commit-0.github.io/", "paper_url": null, "hf_dataset_id": null, "official_leaderboard_url": "https://index.openhands.dev/", "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": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "fable-5", "name": "Fable 5", "vendor": "Anthropic"}, "success_rate": 62.5, "resolved_count": null, "total_count": null, "cost_usd": 12.49, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.18.1", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/95690e32-8d2e-4106-9a37-2f7d424a8494", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 2, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "claude-4-8-opus", "name": "Claude 4.8 Opus", "vendor": "Anthropic"}, "success_rate": 62.5, "resolved_count": null, "total_count": null, "cost_usd": 7.83, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.18.1", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/95f5d2b1-910c-403c-bb17-1b10a033470e", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 3, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "claude-4-7-opus", "name": "Claude 4.7 Opus", "vendor": "Anthropic"}, "success_rate": 56.2, "resolved_count": null, "total_count": null, "cost_usd": 5.69, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/825aa22d-16cb-49c1-8080-97a46db81099", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 4, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "claude-4-6-opus", "name": "Claude 4.6 Opus", "vendor": "Anthropic"}, "success_rate": 56.2, "resolved_count": null, "total_count": null, "cost_usd": 7.69, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/8a792401-ab45-48b6-8398-99a1a7534f69", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 5, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "gpt-5-4", "name": "GPT-5.4", "vendor": "openai"}, "success_rate": 56.2, "resolved_count": null, "total_count": null, "cost_usd": 4.04, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.13.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/04c309cc-564d-465f-8e84-e0b114044609", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 6, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "gpt-5-2", "name": "GPT-5.2", "vendor": "openai"}, "success_rate": 50.0, "resolved_count": null, "total_count": null, "cost_usd": 4.7, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/c343765e-1fdd-494f-96b7-de843c272a36", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 7, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "claude-4-6-sonnet", "name": "Claude 4.6 Sonnet", "vendor": "Anthropic"}, "success_rate": 50.0, "resolved_count": null, "total_count": null, "cost_usd": 6.48, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/a0e8861b-136f-4ff3-be1a-dcf2daa2428a", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 8, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "gpt-5-5", "name": "GPT-5.5", "vendor": "openai"}, "success_rate": 43.8, "resolved_count": null, "total_count": null, "cost_usd": 5.56, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.18.1", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/bab0c2b3-3c08-442d-98e8-7f34bfd76ebd", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 9, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "gpt-5-2-codex", "name": "GPT-5.2 codex", "vendor": "openai"}, "success_rate": 43.8, "resolved_count": null, "total_count": null, "cost_usd": 5.5, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/57c6395a-4cd4-4346-a0c0-4b1209275523", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 10, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "gemini-3-5-flash", "name": "Gemini 3.5 Flash", "vendor": "google"}, "success_rate": 37.5, "resolved_count": null, "total_count": null, "cost_usd": 7.91, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.24.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/f73dcfa9-a6de-4b41-bcf6-abc1d2b0ba58", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 11, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "claude-4-5-opus", "name": "Claude 4.5 Opus", "vendor": "Anthropic"}, "success_rate": 37.5, "resolved_count": null, "total_count": null, "cost_usd": 9.11, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/d15f9cba-5c46-4413-b71d-f7b5d15e6efb", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 12, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "glm-5-1", "name": "GLM 5 1", "vendor": "Zhipu"}, "success_rate": 37.5, "resolved_count": null, "total_count": null, "cost_usd": 5.31, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/069f1865-a4b0-4a67-9451-3043c2ab138c", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 13, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "glm-5", "name": "GLM 5", "vendor": "z-ai"}, "success_rate": 31.2, "resolved_count": null, "total_count": null, "cost_usd": 2.23, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/76ea5306-b580-47c0-a9ad-67a1c995bfba", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 14, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "gemini-3-1-pro", "name": "Gemini 3.1 Pro", "vendor": "Google"}, "success_rate": 25.0, "resolved_count": null, "total_count": null, "cost_usd": 1.18, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/3817b8ac-4a44-42f7-b6ce-08f747db0061", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 15, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "minimax-m3", "name": "MiniMax M3", "vendor": "minimax"}, "success_rate": 25.0, "resolved_count": null, "total_count": null, "cost_usd": 0.62, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.18.1", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/9e4edd2a-981b-40fe-84dd-13c5fc992b42", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 16, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "success_rate": 25.0, "resolved_count": null, "total_count": null, "cost_usd": 1.52, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/65cee637-c137-4253-8fab-616dfbeda695", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 17, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "qwen3-6-plus", "name": "Qwen3.6 Plus", "vendor": "qwen"}, "success_rate": 25.0, "resolved_count": null, "total_count": null, "cost_usd": 7.4936, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/c5f31dca-5471-4ce3-830a-938de77baece", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 18, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "gemini-3-pro", "name": "Gemini 3 Pro", "vendor": "Google"}, "success_rate": 25.0, "resolved_count": null, "total_count": null, "cost_usd": 3.18, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/bfba3513-7461-42da-9944-874848240c29", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 19, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "deepseek-v3-2-reasoner", "name": "DeepSeek V3.2 Reasoner", "vendor": "DeepSeek"}, "success_rate": 25.0, "resolved_count": null, "total_count": null, "cost_usd": 0.57, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/df76145a-e319-468e-ae2e-07f71208496f", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 20, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "qwen3-coder-next", "name": "Qwen3 Coder Next", "vendor": "qwen"}, "success_rate": 25.0, "resolved_count": null, "total_count": null, "cost_usd": 1.04, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/0a1fbe3f-6704-42ad-8b8a-d598dbf493d8", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 21, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "success_rate": 18.8, "resolved_count": null, "total_count": null, "cost_usd": 1.26, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/7f44e8ae-607d-46e7-8f5d-b43abacf8c1b", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 22, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "gemini-3-flash", "name": "Gemini 3 Flash", "vendor": "Google"}, "success_rate": 18.8, "resolved_count": null, "total_count": null, "cost_usd": 2.62, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/3501752b-0081-4611-9807-335281599b80", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 23, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "minimax-2-7", "name": "Minimax 2.7", "vendor": "MiniMax"}, "success_rate": 18.8, "resolved_count": null, "total_count": null, "cost_usd": 0.8926, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.14.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/081a0b7f-fef2-4dad-a267-49f90b2fc866", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 24, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "minimax-m2-1", "name": "MiniMax M2.1", "vendor": "minimax"}, "success_rate": 18.8, "resolved_count": null, "total_count": null, "cost_usd": 0.38, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/6b9df675-af26-4bd6-89b5-d18b38782a92", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 25, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "claude-4-5-sonnet", "name": "Claude 4.5 Sonnet", "vendor": "Anthropic"}, "success_rate": 12.5, "resolved_count": null, "total_count": null, "cost_usd": 3.23, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/17fc5d57-6aae-4dda-8f56-f6275df7db8e", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 26, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "minimax-m2-5", "name": "MiniMax M2.5", "vendor": "minimax"}, "success_rate": 12.5, "resolved_count": null, "total_count": null, "cost_usd": 0.49, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v0.38.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/c06b32df-bf9e-4d10-9e81-93f2c01955a5", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 27, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "glm-4-7", "name": "GLM 4.7", "vendor": "z-ai"}, "success_rate": 12.5, "resolved_count": null, "total_count": null, "cost_usd": 1.64, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/84ad9e18-dc52-4085-bc7f-54205df4fae4", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 28, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "kimi-k2-thinking", "name": "KIMI K2 Thinking", "vendor": "moonshotai"}, "success_rate": 12.5, "resolved_count": null, "total_count": null, "cost_usd": 0.54, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/411cb079-1f09-4779-96b9-4c658df2c0be", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 29, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", "vendor": "deepseek"}, "success_rate": 12.5, "resolved_count": null, "total_count": null, "cost_usd": 0.1577, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.0.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/413fa09a-4b62-451f-9139-9d140a4d108c", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 30, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "qwen3-5-flash", "name": "Qwen3.5 Flash", "vendor": "Qwen"}, "success_rate": 12.5, "resolved_count": null, "total_count": null, "cost_usd": 4.3309, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/2416b7ce-7841-4d7b-b8fb-83ad5c992826", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 31, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "nemotron-3-super", "name": "Nemotron 3 Super", "vendor": "NVIDIA"}, "success_rate": 12.5, "resolved_count": null, "total_count": null, "cost_usd": 1.2153, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.14.0", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/ba725a00-2947-484f-9dad-951071d34c3d", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 32, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "trinity-large-thinking", "name": "Trinity Large Thinking", "vendor": "arcee-ai"}, "success_rate": 12.5, "resolved_count": null, "total_count": null, "cost_usd": 1.2, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.16.1", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/8d97d9a6-f993-44f6-aacd-a6977c811bd3", "observed_at": "2026-07-31T11:38:58.577710"}, {"rank": 33, "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "scaffold_code": "ohsdk", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "homepage_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico", "leaderboard_icon_url": "https://www.swebench.com/img/logos/20241103_OpenHands-CodeAct-2.1-sonnet-20241022.png"}, "model": {"slug": "qwen3-coder-480b", "name": "Qwen3 Coder 480B", "vendor": "Qwen"}, "success_rate": 0.0, "resolved_count": null, "total_count": null, "cost_usd": 0.01, "input_tokens": null, "output_tokens": null, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "is_harnessrl_measured": false, "eval_protocol": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://index.openhands.dev/", "observed_at": "2026-07-31T11:38:58.577710"}]}}