{"model": {"slug": "kimi-k3", "name": "KIMI K3", "vendor": "Moonshot", "model_family": "kimi-k3", "parameter_count_b": null, "context_length": 1048576, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k3", "card_summary": "Moonshot KIMI K3 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 4, "best_success_rate": 87.64, "input_price_per_million": 3.0, "output_price_per_million": 15.0}, "scores": [{"success_rate": 87.64, "resolved_count": null, "total_count": null, "cost_usd": 3.081635541610427, "input_tokens": 5296768, "output_tokens": 54498, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Artificial Analysis Coding Agent Index component (pass@1)", "source": "artificialanalysis", "source_url": "https://artificialanalysis.ai/agents/coding-agents", "observed_at": "2026-08-27T21:54:11.189561+00:00", "harness": {"slug": "kimi-code-cli", "name": "Kimi Code CLI", "vendor": "Moonshot", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k3", "name": "KIMI K3", "vendor": "Moonshot"}, "benchmark": {"slug": "terminal-bench-v2-1", "name": "Terminal-Bench v2.1 (AA component)"}}, {"success_rate": 63.72, "resolved_count": null, "total_count": null, "cost_usd": 3.081635541610427, "input_tokens": 5296768, "output_tokens": 54498, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Artificial Analysis Coding Agent Index component (pass@1)", "source": "artificialanalysis", "source_url": "https://artificialanalysis.ai/agents/coding-agents", "observed_at": "2026-08-27T21:54:11.189561+00:00", "harness": {"slug": "kimi-code-cli", "name": "Kimi Code CLI", "vendor": "Moonshot", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k3", "name": "KIMI K3", "vendor": "Moonshot"}, "benchmark": {"slug": "deepswe", "name": "DeepSWE (AA component)"}}, {"success_rate": 54.5, "resolved_count": null, "total_count": null, "cost_usd": 0.668, "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-k3", "name": "KIMI K3", "vendor": "Moonshot"}, "benchmark": {"slug": "wildclawbench", "name": "WildClawBench"}}, {"success_rate": 36.56, "resolved_count": null, "total_count": null, "cost_usd": 3.081635541610427, "input_tokens": 5296768, "output_tokens": 54498, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": null, "harness_version": null, "trial_count": null, "is_harnessrl_measured": false, "eval_protocol": "Artificial Analysis Coding Agent Index component (pass@1)", "source": "artificialanalysis", "source_url": "https://artificialanalysis.ai/agents/coding-agents", "observed_at": "2026-08-27T21:54:11.189561+00:00", "harness": {"slug": "kimi-code-cli", "name": "Kimi Code CLI", "vendor": "Moonshot", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k3", "name": "KIMI K3", "vendor": "Moonshot"}, "benchmark": {"slug": "swe-atlas-qna", "name": "SWE-Atlas-QnA (AA component)"}}], "harnesses": [{"slug": "kimi-code-cli", "name": "Kimi Code CLI", "vendor": "Moonshot", "repo_url": "https://github.com/MoonshotAI/Kimi-Dev", "openrouter_icon_url": null}, {"slug": "openclaw", "name": "OpenClaw", "vendor": "OpenClaw", "repo_url": "https://github.com/openclaw/openclaw", "openrouter_icon_url": null}]}