{"benchmark": {"slug": "swt-bench", "name": "SWT-Bench", "description": "SWT-Bench measures test-generation and testing quality. OpenHands Index rows use OpenHands SDK (`openhands_index`). Official site submissions use swtbench.com \u2014 distinct eval configs from OH Index runs.", "category": "eval", "split": null, "language": null, "task_count": null, "homepage_url": "https://swtbench.com/", "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": 91.9}, "protocol": {"eval_protocol": "OpenHands SDK v1.8.3", "temperature": null, "max_turns": null, "context_budget_tokens": null, "n": 12}, "rankings": {"benchmark": {"slug": "swt-bench", "name": "SWT-Bench", "description": "SWT-Bench measures test-generation and testing quality. OpenHands Index rows use OpenHands SDK (`openhands_index`). Official site submissions use swtbench.com \u2014 distinct eval configs from OH Index runs.", "category": "eval", "split": null, "language": null, "task_count": null, "homepage_url": "https://swtbench.com/", "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": 91.9, "resolved_count": null, "total_count": null, "cost_usd": 1.47, "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/e927fb1c-feb7-4d96-9e2c-f969cd6feccb", "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": 84.3, "resolved_count": null, "total_count": null, "cost_usd": 0.73, "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/efde50d3-3151-48fc-aac2-c98a80d7406e", "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": "gpt-5-5", "name": "GPT-5.5", "vendor": "openai"}, "success_rate": 83.4, "resolved_count": null, "total_count": null, "cost_usd": 0.92, "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/6eec49a3-ecfb-4081-8282-caf1e3e1dda0", "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": "minimax-m3", "name": "MiniMax M3", "vendor": "minimax"}, "success_rate": 81.1, "resolved_count": null, "total_count": null, "cost_usd": 0.11, "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 v1.18.1", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/2203b457-5c29-4b00-be91-c0408f119244", "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": "claude-4-7-opus", "name": "Claude 4.7 Opus", "vendor": "Anthropic"}, "success_rate": 80.8, "resolved_count": null, "total_count": null, "cost_usd": 0.82, "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/96a4370b-a553-4c91-951b-79ae3a93979d", "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": "claude-4-6-opus", "name": "Claude 4.6 Opus", "vendor": "Anthropic"}, "success_rate": 78.8, "resolved_count": null, "total_count": null, "cost_usd": 0.43, "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/cbf7f857-21d0-4526-b830-25d4e88ab0ed", "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-4-5-opus", "name": "Claude 4.5 Opus", "vendor": "Anthropic"}, "success_rate": 78.5, "resolved_count": null, "total_count": null, "cost_usd": 1.38, "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://index.openhands.dev/", "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": "gemini-3-5-flash", "name": "Gemini 3.5 Flash", "vendor": "google"}, "success_rate": 76.2, "resolved_count": null, "total_count": null, "cost_usd": 1.03, "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/88a0e23e-741b-4eba-a6a6-87056fb23905", "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": "gemini-3-1-pro", "name": "Gemini 3.1 Pro", "vendor": "Google"}, "success_rate": 75.1, "resolved_count": null, "total_count": null, "cost_usd": 1.62, "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 v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/c44c25a6-214d-4f87-aa3c-fdb8c3531d13", "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": "gpt-5-2", "name": "GPT-5.2", "vendor": "openai"}, "success_rate": 73.2, "resolved_count": null, "total_count": null, "cost_usd": 0.56, "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 v1.8.3", "source": "openhands_index", "source_url": "https://index.openhands.dev/", "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": "gemini-3-flash", "name": "Gemini 3 Flash", "vendor": "Google"}, "success_rate": 70.7, "resolved_count": null, "total_count": null, "cost_usd": 0.3, "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"}, {"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": "gpt-5-4", "name": "GPT-5.4", "vendor": "openai"}, "success_rate": 70.4, "resolved_count": null, "total_count": null, "cost_usd": 0.47, "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/90cebe80-49bb-40c1-b65b-78f5e40461f9", "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": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "success_rate": 70.4, "resolved_count": null, "total_count": null, "cost_usd": 0.33, "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/9a4d9991-37b4-44a1-acff-2057c6525748", "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": "glm-5-1", "name": "GLM 5 1", "vendor": "Zhipu"}, "success_rate": 70.2, "resolved_count": null, "total_count": null, "cost_usd": 0.76, "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/edae3592-9be7-4da5-83c3-b6ebe10e1bf6", "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-2-7", "name": "Minimax 2.7", "vendor": "MiniMax"}, "success_rate": 69.1, "resolved_count": null, "total_count": null, "cost_usd": 0.1283, "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/f42deebe-f174-41f7-96e8-3e2fbc8a61d7", "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": "claude-4-5-sonnet", "name": "Claude 4.5 Sonnet", "vendor": "Anthropic"}, "success_rate": 68.8, "resolved_count": null, "total_count": null, "cost_usd": 0.98, "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"}, {"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": "gemini-3-pro", "name": "Gemini 3 Pro", "vendor": "Google"}, "success_rate": 68.6, "resolved_count": null, "total_count": null, "cost_usd": 1.01, "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"}, {"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": "minimax-m2-5", "name": "MiniMax M2.5", "vendor": "minimax"}, "success_rate": 68.1, "resolved_count": null, "total_count": null, "cost_usd": 0.2239, "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/9bbf1e2a-6085-4a0a-b68f-357f417f4012", "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-v4-pro", "name": "DeepSeek V4 Pro", "vendor": "deepseek"}, "success_rate": 68.1, "resolved_count": null, "total_count": null, "cost_usd": 0.0354, "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/4e693e26-5442-4d6a-9ee4-bdd26fc39213", "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": "gpt-5-2-codex", "name": "GPT-5.2 codex", "vendor": "openai"}, "success_rate": 67.0, "resolved_count": null, "total_count": null, "cost_usd": 0.66, "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"}, {"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": "qwen3-6-plus", "name": "Qwen3.6 Plus", "vendor": "qwen"}, "success_rate": 62.1, "resolved_count": null, "total_count": null, "cost_usd": 2.085, "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/d5c3aa56-4cbd-4bac-9dfa-8d85cc25e994", "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": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "success_rate": 61.9, "resolved_count": null, "total_count": null, "cost_usd": 0.4246, "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"}, {"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-m2-1", "name": "MiniMax M2.1", "vendor": "minimax"}, "success_rate": 61.4, "resolved_count": null, "total_count": null, "cost_usd": 0.5441, "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"}, {"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": "claude-4-6-sonnet", "name": "Claude 4.6 Sonnet", "vendor": "Anthropic"}, "success_rate": 54.0, "resolved_count": null, "total_count": null, "cost_usd": 0.87, "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/17b3fd34-7334-4c67-a510-cf2e094998c2", "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": "deepseek-v3-2-reasoner", "name": "DeepSeek V3.2 Reasoner", "vendor": "DeepSeek"}, "success_rate": 53.6, "resolved_count": null, "total_count": null, "cost_usd": 0.12, "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"}, {"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": "glm-4-7", "name": "GLM 4.7", "vendor": "z-ai"}, "success_rate": 49.4, "resolved_count": null, "total_count": null, "cost_usd": 0.37, "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"}, {"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-5", "name": "GLM 5", "vendor": "z-ai"}, "success_rate": 47.3, "resolved_count": null, "total_count": null, "cost_usd": 0.91, "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 v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/a7d29286-6810-4ca8-8a11-21d6ae33822b", "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": 47.3, "resolved_count": null, "total_count": null, "cost_usd": 1.39, "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"}, {"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": "qwen3-coder-next", "name": "Qwen3 Coder Next", "vendor": "qwen"}, "success_rate": 45.7, "resolved_count": null, "total_count": null, "cost_usd": 1.1, "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/a9302f07-92a9-48cb-9964-d91280be4d28", "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": "nemotron-3-super", "name": "Nemotron 3 Super", "vendor": "NVIDIA"}, "success_rate": 45.7, "resolved_count": null, "total_count": null, "cost_usd": 0.3333, "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/01e58390-f947-4dcc-8d34-5e8c61bd3788", "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": "qwen3-5-flash", "name": "Qwen3.5 Flash", "vendor": "Qwen"}, "success_rate": 38.3, "resolved_count": null, "total_count": null, "cost_usd": 1.7107, "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/4ef023af-364e-4ba6-ac3d-19336bd4af18", "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": "qwen3-coder-480b", "name": "Qwen3 Coder 480B", "vendor": "Qwen"}, "success_rate": 34.9, "resolved_count": null, "total_count": null, "cost_usd": 0.97, "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"}, {"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": "trinity-large-thinking", "name": "Trinity Large Thinking", "vendor": "arcee-ai"}, "success_rate": 33.3, "resolved_count": null, "total_count": null, "cost_usd": 0.8, "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/5de44f24-5b10-4b75-a52d-05184f894a7e", "observed_at": "2026-07-31T11:38:58.577710"}]}}