{"model": {"slug": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek", "model_family": "deepseek-v3", "parameter_count_b": null, "context_length": 128000, "homepage_url": null, "hf_model_id": null, "openrouter_id": null, "card_summary": "DeepSeek DeepSeek V3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 5, "best_success_rate": 49.55, "input_price_per_million": null, "output_price_per_million": null}, "scores": [{"success_rate": 49.55, "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": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek"}, "benchmark": {"slug": "livecodebench-generation", "name": "LiveCodeBench (code generation)"}}, {"success_rate": 43.16, "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": "SWE-rebench resolved rate (best rolling window)", "source": "swe_rebench_site", "source_url": "https://swe-rebench.com/", "observed_at": null, "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek"}, "benchmark": {"slug": "swe-rebench", "name": "SWE-rebench"}}, {"success_rate": 42.0, "resolved_count": 210, "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/YerbaPage/SWE-Exp", "observed_at": "2025-08-06T00:00:00+00:00", "harness": {"slug": "swe-exp", "name": "SWE Exp", "vendor": "Yerbapage", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek"}, "benchmark": {"slug": "swe-bench-verified", "name": "SWE-bench Verified"}}, {"success_rate": 36.67, "resolved_count": 110, "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/GLEAM-Lab/KGCompass", "observed_at": "2025-06-09T00:00:00+00:00", "harness": {"slug": "kgcompass", "name": "KGCompass", "vendor": "Gleam Lab", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek"}, "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": null, "openrouter_icon_url": null}, "model": {"slug": "deepseek-v3", "name": "DeepSeek V3", "vendor": "DeepSeek"}, "benchmark": {"slug": "swe-bench-lite", "name": "SWE-bench Lite"}}], "harnesses": [{"slug": "kgcompass", "name": "KGCompass", "vendor": "Gleam Lab", "repo_url": "https://github.com/GLEAM-Lab/KGCompass", "openrouter_icon_url": null}, {"slug": "livecodebench", "name": "Livecodebench", "vendor": "LiveCodeBench", "repo_url": "https://github.com/LiveCodeBench/LiveCodeBench", "openrouter_icon_url": null}, {"slug": "moatless-tools", "name": "Moatless Tools", "vendor": "Aorwall", "repo_url": "https://github.com/aorwall/moatless-tools", "openrouter_icon_url": null}, {"slug": "swe-exp", "name": "SWE Exp", "vendor": "Yerbapage", "repo_url": "https://github.com/YerbaPage/SWE-Exp", "openrouter_icon_url": null}, {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null}]}