{"harness": {"slug": "moatless-tools", "name": "Moatless Tools", "vendor": "Aorwall", "description": "Moatless Tools is an agentic coding toolkit (Moatless / aorwall ecosystem) with public SWE-bench Verified leaderboard entries. The harness provides structured tools and workflows for repository editing and issue resolution benchmarks.\n\nRelated infrastructure repos (for example SWE-bench docker tooling) sometimes appear in submission metadata; the agent loop itself is documented under `aorwall/moatless-tools`.\n\nCommunity `swe_bench_site` scores only. Compare against Moatless rows with matching model and submission date \u2014 Moatless is not interchangeable with SWE-agent or OpenHands without reading each `source_url`.", "card_summary": "Moatless Tools agent scaffold \u2014 SWE-bench Verified community submissions.", "homepage_url": "https://github.com/aorwall/moatless-tools", "repo_url": "https://github.com/aorwall/moatless-tools", "docs_url": null, "scaffold_code": null, "harbor_agent_name": null, "api_protocol": "openai", "status": "validated", "supports_rl": true, "score_count": 5, "best_success_rate": 70.8, "github_stars": 1200, "popularity_tier": null, "hrl_score": 31.0, "hrl_rank": 26, "catalog_token_volume": null, "openrouter_icon_url": null, "leaderboard_icon_url": "https://www.swebench.com/img/logos/20240617_moatless_gpt4o.png", "aa_coding_index": null, "aa_mean_cost_usd": null, "aa_mean_total_tokens": null}, "scores": [{"success_rate": 70.8, "resolved_count": 354, "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/aorwall/moatless-tools", "observed_at": "2025-06-11T00:00:00+00:00", "harness": {"slug": "moatless-tools", "name": "Moatless Tools", "vendor": "Aorwall", "repo_url": "https://github.com/aorwall/moatless-tools", "openrouter_icon_url": null}, "model": {"slug": "claude-4-sonnet", "name": "Claude 4 Sonnet", "vendor": "Anthropic"}, "benchmark": {"slug": "swe-bench-verified", "name": "SWE-bench Verified"}}, {"success_rate": 38.33, "resolved_count": 115, "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/aorwall/moatless-tools", "observed_at": "2024-11-17T00:00:00+00:00", "harness": {"slug": "moatless-tools", "name": "Moatless Tools", "vendor": "Aorwall", "repo_url": "https://github.com/aorwall/moatless-tools", "openrouter_icon_url": null}, "model": {"slug": "claude-3-5-sonnet-20241022", "name": "Claude 3.5 Sonnet (2024-10-22)", "vendor": "Anthropic"}, "benchmark": {"slug": "swe-bench-lite", "name": "SWE-bench Lite"}}, {"success_rate": 30.67, "resolved_count": 92, "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/aorwall/moatless-tools", "observed_at": "2025-01-11T00:00:00+00:00", "harness": {"slug": "moatless-tools", "name": "Moatless Tools", "vendor": "Aorwall", "repo_url": "https://github.com/aorwall/moatless-tools", "openrouter_icon_url": null}, "model": {"slug": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek"}, "benchmark": {"slug": "swe-bench-lite", "name": "SWE-bench Lite"}}, {"success_rate": 26.67, "resolved_count": 80, "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/aorwall/moatless-tools", "observed_at": "2024-06-23T00:00:00+00:00", "harness": {"slug": "moatless-tools", "name": "Moatless Tools", "vendor": "Aorwall", "repo_url": "https://github.com/aorwall/moatless-tools", "openrouter_icon_url": null}, "model": {"slug": "claude-3-5-sonnet", "name": "Claude 3.5 Sonnet", "vendor": "Anthropic"}, "benchmark": {"slug": "swe-bench-lite", "name": "SWE-bench Lite"}}, {"success_rate": 24.67, "resolved_count": 74, "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/aorwall/moatless-tools", "observed_at": "2024-06-17T00:00:00+00:00", "harness": {"slug": "moatless-tools", "name": "Moatless Tools", "vendor": "Aorwall", "repo_url": "https://github.com/aorwall/moatless-tools", "openrouter_icon_url": null}, "model": {"slug": "gpt-4o-20240513", "name": "GPT-4o (2024-05-13)", "vendor": "OpenAI"}, "benchmark": {"slug": "swe-bench-lite", "name": "SWE-bench Lite"}}], "benchmarks": [{"slug": "swe-bench-lite", "name": "SWE-bench Lite", "category": "eval"}, {"slug": "swe-bench-verified", "name": "SWE-bench Verified", "category": "eval"}]}