{"model": {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot", "model_family": "kimi-k2-6", "parameter_count_b": null, "context_length": 262144, "homepage_url": null, "hf_model_id": null, "openrouter_id": "moonshotai/kimi-k2.6", "card_summary": "Moonshot KIMI K2.6 on SWE-bench Verified leaderboards.", "is_rl_checkpoint": false, "score_count": 9, "best_success_rate": 74.6, "input_price_per_million": 0.95, "output_price_per_million": 4.0}, "scores": [{"success_rate": 74.6, "resolved_count": null, "total_count": null, "cost_usd": 0.67, "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 v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/e024c27b-0bc2-437c-8b36-f3695942dcef", "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-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "openhands-swe-bench", "name": "SWE-bench (OpenHands Index)"}}, {"success_rate": 74.5, "resolved_count": null, "total_count": null, "cost_usd": 0.42, "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 v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/f9cb5c66-98fb-48d9-87d6-08d7b16e66c3", "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-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "gaia", "name": "GAIA"}}, {"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, "harness_version": null, "trial_count": 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", "harness": {"slug": "openhands-sdk", "name": "OpenHands SDK", "vendor": "All Hands AI", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "swt-bench", "name": "SWT-Bench"}}, {"success_rate": 69.29, "resolved_count": null, "total_count": null, "cost_usd": 1.2171000741104296, "input_tokens": 5891966, "output_tokens": 36930, "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": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "terminal-bench-v2-1", "name": "Terminal-Bench v2.1 (AA component)"}}, {"success_rate": 54.67, "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-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "swe-rebench", "name": "SWE-rebench"}}, {"success_rate": 41.2, "resolved_count": null, "total_count": null, "cost_usd": 0.64, "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 v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/bf318301-2c72-4fe2-a705-d104161d05c0", "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-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "swe-bench-multimodal", "name": "SWE-bench Multimodal (OpenHands Index)"}}, {"success_rate": 25.0, "resolved_count": null, "total_count": null, "cost_usd": 1.52, "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 v1.11.5", "source": "openhands_index", "source_url": "https://laminar.sh/shared/evals/65cee637-c137-4253-8fab-616dfbeda695", "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-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "commit0", "name": "Commit0"}}, {"success_rate": 16.52, "resolved_count": null, "total_count": null, "cost_usd": 1.2171000741104296, "input_tokens": 5891966, "output_tokens": 36930, "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": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "deepswe", "name": "DeepSWE (AA component)"}}, {"success_rate": 15.86, "resolved_count": null, "total_count": null, "cost_usd": 1.2171000741104296, "input_tokens": 5891966, "output_tokens": 36930, "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": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "repo_url": null, "openrouter_icon_url": null}, "model": {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "benchmark": {"slug": "swe-atlas-qna", "name": "SWE-Atlas-QnA (AA component)"}}], "harnesses": [{"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "repo_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico"}, {"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}]}