{"model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai", "model_family": "kimi-k2-5", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k2.5", "card_summary": "moonshotai KIMI K2.5 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 8, "best_success_rate": 68.8, "input_price_per_million": 0.6, "output_price_per_million": 3.0}, "scores": [{"success_rate": 68.8, "resolved_count": null, "total_count": null, "cost_usd": 0.4063, "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": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://index.openhands.dev/", "observed_at": "2026-07-31T11:38:58.577710", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "openhands-swe-bench", "name": "SWE-bench (OpenHands Index)"}}, {"success_rate": 67.3, "resolved_count": 202, "total_count": 300, "cost_usd": 0.6928368501333334, "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 Multilingual (mini-SWE-agent)", "source": "swe_bench_site", "source_url": "https://moonshotai.github.io/Kimi-K2/", "observed_at": "2026-02-13T00:00:00+00:00", "harness": {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "swe-bench-multilingual", "name": "SWE-bench Multilingual"}}, {"success_rate": 63.6, "resolved_count": null, "total_count": null, "cost_usd": 0.3781, "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": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://index.openhands.dev/", "observed_at": "2026-07-31T11:38:58.577710", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "gaia", "name": "GAIA"}}, {"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, "harness_version": null, "trial_count": 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", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "swt-bench", "name": "SWT-Bench"}}, {"success_rate": 61.33, "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": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "swe-rebench", "name": "SWE-rebench"}}, {"success_rate": 32.8, "resolved_count": null, "total_count": null, "cost_usd": 1.6213, "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": "OpenHands SDK v1.8.3", "source": "openhands_index", "source_url": "https://index.openhands.dev/", "observed_at": "2026-07-31T11:38:58.577710", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "swe-bench-multimodal", "name": "SWE-bench Multimodal (OpenHands Index)"}}, {"success_rate": 30.8, "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, "harness_version": null, "trial_count": 60, "is_harnessrl_measured": false, "eval_protocol": "WildClawBench overall score (60 tasks)", "source": "wildclawbench_site", "source_url": "https://github.com/internlm/WildClawBench", "observed_at": null, "harness": {"slug": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"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, "harness_version": null, "trial_count": 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", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-5", "name": "KIMI K2.5", "vendor": "moonshotai"}, "benchmark": {"slug": "commit0", "name": "Commit0"}}], "harnesses": [{"slug": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}, {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": "https://github.com/All-Hands-AI/OpenHands", "openrouter_icon_url": "https://www.all-hands.dev/favicon.ico"}, {"slug": "mini-swe-agent", "name": "mini-SWE-agent", "vendor": "anthropic", "repo_url": "https://github.com/SWE-agent/mini-swe-agent", "openrouter_icon_url": null}]}