{"benchmark": {"slug": "terminal-bench-v2-1", "name": "Terminal-Bench v2.1 (AA component)", "description": "Terminal-Bench v2.1 on Artificial Analysis evaluates agents in interactive terminal environments (shell workflows, CLI tools). Scores appear as AA component rows (`artificialanalysis`).\n\nNot the official [tbench.ai TB 2.1 leaderboard](https://www.tbench.ai/leaderboard/terminal-bench/2.1) matrix. Harbor Hub hosts the maintainer leaderboard \u2014 catalog ingest for official TB 2.1 is on the watchlist.", "category": "eval", "split": null, "language": null, "task_count": null, "homepage_url": "https://artificialanalysis.ai/agents/coding-agents", "paper_url": null, "hf_dataset_id": null, "official_leaderboard_url": "https://www.tbench.ai/leaderboard/terminal-bench/2.1", "is_public_leaderboard": true, "harness_count": 10, "model_count": 40, "score_count": 45, "best_success_rate": 91.01}, "protocol": {"eval_protocol": "Artificial Analysis Coding Agent Index component (pass@1)", "temperature": null, "max_turns": null, "context_budget_tokens": null, "n": 45}, "rankings": {"benchmark": {"slug": "terminal-bench-v2-1", "name": "Terminal-Bench v2.1 (AA component)", "description": "Terminal-Bench v2.1 on Artificial Analysis evaluates agents in interactive terminal environments (shell workflows, CLI tools). Scores appear as AA component rows (`artificialanalysis`).\n\nNot the official [tbench.ai TB 2.1 leaderboard](https://www.tbench.ai/leaderboard/terminal-bench/2.1) matrix. Harbor Hub hosts the maintainer leaderboard \u2014 catalog ingest for official TB 2.1 is on the watchlist.", "category": "eval", "split": null, "language": null, "task_count": null, "homepage_url": "https://artificialanalysis.ai/agents/coding-agents", "paper_url": null, "hf_dataset_id": null, "official_leaderboard_url": "https://www.tbench.ai/leaderboard/terminal-bench/2.1", "is_public_leaderboard": true, "harness_count": null, "model_count": null, "score_count": null, "best_success_rate": null}, "sort": "success_rate", "rows": [{"rank": 1, "harness": {"slug": "opencode", "name": "OpenCode", "vendor": "SST", "scaffold_code": "oc", "repo_url": "https://github.com/sst/opencode", "homepage_url": "https://github.com/sst/opencode", "openrouter_icon_url": "https://opencode.ai/favicon.ico", "leaderboard_icon_url": "https://github.com/sst/opencode/raw/dev/packages/web/public/favicon.ico"}, "model": {"slug": "gemini-3-7-flash-high", "name": "Gemini 3.7 Flash (high)", "vendor": "Google"}, "success_rate": 91.01, "resolved_count": null, "total_count": null, "cost_usd": 1.2679325688650294, "input_tokens": 9497213, "output_tokens": 49098, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 2, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-5-opus-xhigh", "name": "Claude 5 Opus (xhigh)", "vendor": "Anthropic"}, "success_rate": 89.14, "resolved_count": null, "total_count": null, "cost_usd": 8.170783921523505, "input_tokens": 10747525, "output_tokens": 73273, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 3, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-5-opus-max", "name": "Claude 5 Opus (max)", "vendor": "Anthropic"}, "success_rate": 88.76, "resolved_count": null, "total_count": null, "cost_usd": 8.943547018021487, "input_tokens": 11810977, "output_tokens": 81385, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 4, "harness": {"slug": "kimi-code-cli", "name": "Kimi Code CLI", "vendor": "Moonshot", "scaffold_code": null, "repo_url": "https://github.com/MoonshotAI/Kimi-Dev", "homepage_url": "https://kimi.moonshot.cn", "openrouter_icon_url": null, "leaderboard_icon_url": null}, "model": {"slug": "kimi-k3", "name": "KIMI K3", "vendor": "Moonshot"}, "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, "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"}, {"rank": 5, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-5-opus-high", "name": "Claude 5 Opus (high)", "vendor": "Anthropic"}, "success_rate": 86.89, "resolved_count": null, "total_count": null, "cost_usd": 3.918602446063396, "input_tokens": 4937399, "output_tokens": 37331, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 6, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "fable-5-max-with-fallback", "name": "Fable 5 Max With Fallback", "vendor": "Fable"}, "success_rate": 86.52, "resolved_count": null, "total_count": null, "cost_usd": 11.687407620910031, "input_tokens": 6901095, "output_tokens": 74265, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 7, "harness": {"slug": "antigravity-sdk-v0-1-8", "name": "Antigravity Sdk V0 1 8", "vendor": "Antigravity", "scaffold_code": null, "repo_url": null, "homepage_url": "https://antigravity.dev", "openrouter_icon_url": null, "leaderboard_icon_url": null}, "model": {"slug": "gemini-3-7-flash-high", "name": "Gemini 3.7 Flash (high)", "vendor": "Google"}, "success_rate": 86.52, "resolved_count": null, "total_count": null, "cost_usd": 1.396316917192255, "input_tokens": 7938344, "output_tokens": 64430, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 8, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-5-opus-medium", "name": "Claude 5 Opus (medium)", "vendor": "Anthropic"}, "success_rate": 85.02, "resolved_count": null, "total_count": null, "cost_usd": 3.1718671924846644, "input_tokens": 3984815, "output_tokens": 30206, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 9, "harness": {"slug": "grok-build", "name": "Grok Build", "vendor": "xAI", "scaffold_code": null, "repo_url": "https://github.com/xai-org/grok", "homepage_url": "https://x.ai", "openrouter_icon_url": null, "leaderboard_icon_url": null}, "model": {"slug": "grok-4-5-high", "name": "GROK 4.5 (high)", "vendor": "xAI"}, "success_rate": 84.27, "resolved_count": null, "total_count": null, "cost_usd": 2.4389824437627774, "input_tokens": 1837535, "output_tokens": 25699, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 10, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "qwen3-8-max", "name": "Qwen3.8 Max", "vendor": "Qwen"}, "success_rate": 83.9, "resolved_count": null, "total_count": null, "cost_usd": 3.2306109660020477, "input_tokens": 6469207, "output_tokens": 63117, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 11, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-8-opus-max", "name": "Claude 4.8 Opus (max)", "vendor": "Anthropic"}, "success_rate": 83.9, "resolved_count": null, "total_count": null, "cost_usd": 7.724725797009217, "input_tokens": 8919829, "output_tokens": 89374, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 12, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-8-opus-xhigh", "name": "Claude 4.8 Opus (xhigh)", "vendor": "Anthropic"}, "success_rate": 83.15, "resolved_count": null, "total_count": null, "cost_usd": 5.665366469580767, "input_tokens": 6783846, "output_tokens": 62541, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 13, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-5-xhigh", "name": "GPT-5.5 (xhigh)", "vendor": "OpenAI"}, "success_rate": 82.77, "resolved_count": null, "total_count": null, "cost_usd": 4.7523700715746395, "input_tokens": 6164087, "output_tokens": 25286, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 14, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-8-opus-high", "name": "Claude 4.8 Opus (high)", "vendor": "Anthropic"}, "success_rate": 82.4, "resolved_count": null, "total_count": null, "cost_usd": 3.7823013803680996, "input_tokens": 4574601, "output_tokens": 40682, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 15, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-5-opus-low", "name": "Claude 5 Opus (low)", "vendor": "Anthropic"}, "success_rate": 82.02, "resolved_count": null, "total_count": null, "cost_usd": 2.2951577448875273, "input_tokens": 2618171, "output_tokens": 22632, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 16, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-8-opus-medium", "name": "Claude 4.8 Opus (medium)", "vendor": "Anthropic"}, "success_rate": 82.02, "resolved_count": null, "total_count": null, "cost_usd": 3.3038416339468313, "input_tokens": 3898584, "output_tokens": 34668, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 17, "harness": {"slug": "muse-code", "name": "Muse Code", "vendor": "Muse", "scaffold_code": null, "repo_url": null, "homepage_url": "https://muse.ai", "openrouter_icon_url": null, "leaderboard_icon_url": null}, "model": {"slug": "muse-spark-1-2-xhigh", "name": "Muse Spark 1 2 Xhigh", "vendor": "Muse"}, "success_rate": 81.65, "resolved_count": null, "total_count": null, "cost_usd": 2.072823051942741, "input_tokens": 10093761, "output_tokens": 58305, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 18, "harness": {"slug": "opencode", "name": "OpenCode", "vendor": "SST", "scaffold_code": "oc", "repo_url": "https://github.com/sst/opencode", "homepage_url": "https://github.com/sst/opencode", "openrouter_icon_url": "https://opencode.ai/favicon.ico", "leaderboard_icon_url": "https://github.com/sst/opencode/raw/dev/packages/web/public/favicon.ico"}, "model": {"slug": "muse-spark-1-2-xhigh", "name": "Muse Spark 1 2 Xhigh", "vendor": "Muse"}, "success_rate": 79.78, "resolved_count": null, "total_count": null, "cost_usd": 1.914379785695295, "input_tokens": 8360784, "output_tokens": 47157, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 19, "harness": {"slug": "devin-cli", "name": "Devin CLI", "vendor": "Cognition", "scaffold_code": null, "repo_url": "https://github.com/CognitionAI/devin-cli", "homepage_url": "https://artificialanalysis.ai/agents/coding-agents", "openrouter_icon_url": null, "leaderboard_icon_url": null}, "model": {"slug": "swe-1-7-lightning-max", "name": "SWE 1.7 Lightning Max", "vendor": null}, "success_rate": 79.4, "resolved_count": null, "total_count": null, "cost_usd": 8.521259638036815, "input_tokens": 7834231, "output_tokens": 38917, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 20, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-5-medium", "name": "GPT-5.5 (medium)", "vendor": "OpenAI"}, "success_rate": 78.65, "resolved_count": null, "total_count": null, "cost_usd": 2.6525358742331298, "input_tokens": 3492715, "output_tokens": 13239, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 21, "harness": {"slug": "opencode", "name": "OpenCode", "vendor": "SST", "scaffold_code": "oc", "repo_url": "https://github.com/sst/opencode", "homepage_url": "https://github.com/sst/opencode", "openrouter_icon_url": "https://opencode.ai/favicon.ico", "leaderboard_icon_url": "https://github.com/sst/opencode/raw/dev/packages/web/public/favicon.ico"}, "model": {"slug": "gemini-3-6-flash-high", "name": "Gemini 3.6 Flash (high)", "vendor": "Google"}, "success_rate": 78.65, "resolved_count": null, "total_count": null, "cost_usd": 2.0838901547546023, "input_tokens": 6765842, "output_tokens": 42763, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 22, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-6-max", "name": "GPT-5.6 (max)", "vendor": "OpenAI"}, "success_rate": 78.28, "resolved_count": null, "total_count": null, "cost_usd": 2.695350269529651, "input_tokens": 4933733, "output_tokens": 37445, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 23, "harness": {"slug": "opencode", "name": "OpenCode", "vendor": "SST", "scaffold_code": "oc", "repo_url": "https://github.com/sst/opencode", "homepage_url": "https://github.com/sst/opencode", "openrouter_icon_url": "https://opencode.ai/favicon.ico", "leaderboard_icon_url": "https://github.com/sst/opencode/raw/dev/packages/web/public/favicon.ico"}, "model": {"slug": "claude-4-7-opus-medium", "name": "Claude 4.7 Opus (medium)", "vendor": "Anthropic"}, "success_rate": 78.28, "resolved_count": null, "total_count": null, "cost_usd": 2.942840985557261, "input_tokens": 3744700, "output_tokens": 25943, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 24, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-6-low", "name": "GPT-5.6 (low)", "vendor": "OpenAI"}, "success_rate": 77.9, "resolved_count": null, "total_count": null, "cost_usd": 1.2924588445807745, "input_tokens": 1658130, "output_tokens": 8962, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 25, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-8-opus-low", "name": "Claude 4.8 Opus (low)", "vendor": "Anthropic"}, "success_rate": 77.9, "resolved_count": null, "total_count": null, "cost_usd": 2.1825946797034774, "input_tokens": 2595804, "output_tokens": 23270, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 26, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-7-opus-max", "name": "Claude 4.7 Opus (max)", "vendor": "Anthropic"}, "success_rate": 77.53, "resolved_count": null, "total_count": null, "cost_usd": 5.915424259100206, "input_tokens": 8042457, "output_tokens": 47224, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 27, "harness": {"slug": "opencode", "name": "OpenCode", "vendor": "SST", "scaffold_code": "oc", "repo_url": "https://github.com/sst/opencode", "homepage_url": "https://github.com/sst/opencode", "openrouter_icon_url": "https://opencode.ai/favicon.ico", "leaderboard_icon_url": "https://github.com/sst/opencode/raw/dev/packages/web/public/favicon.ico"}, "model": {"slug": "muse-spark-1-1-xhigh", "name": "Muse Spark 1.1 (xhigh)", "vendor": "Muse"}, "success_rate": 77.15, "resolved_count": null, "total_count": null, "cost_usd": 1.4352184351738226, "input_tokens": 6284599, "output_tokens": 34558, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 28, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-7-opus-medium", "name": "Claude 4.7 Opus (medium)", "vendor": "Anthropic"}, "success_rate": 77.15, "resolved_count": null, "total_count": null, "cost_usd": 1.8006617447341524, "input_tokens": 2310268, "output_tokens": 17168, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 29, "harness": {"slug": "cursor-cli", "name": "Cursor CLI", "vendor": "Cursor", "scaffold_code": null, "repo_url": "https://github.com/getcursor/cursor", "homepage_url": "https://cursor.com", "openrouter_icon_url": "https://cursor.com/apple-touch-icon.png", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-5-medium", "name": "GPT-5.5 (medium)", "vendor": "OpenAI"}, "success_rate": 76.4, "resolved_count": null, "total_count": null, "cost_usd": 1.9980312342194944, "input_tokens": 2043912, "output_tokens": 11032, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 30, "harness": {"slug": "gemini-cli", "name": "Gemini CLI", "vendor": "Google", "scaffold_code": null, "repo_url": "https://github.com/google-gemini/gemini-cli", "homepage_url": "https://github.com/google-gemini/gemini-cli", "openrouter_icon_url": "https://www.gstatic.com/lamda/images/gemini_favicon_f06995846fc77c897+24.png", "leaderboard_icon_url": null}, "model": {"slug": "gemini-3-1-pro-high", "name": "Gemini 3.1 Pro (high)", "vendor": "Google"}, "success_rate": 76.03, "resolved_count": null, "total_count": null, "cost_usd": 1.0400415618609393, "input_tokens": 2465901, "output_tokens": 12977, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 31, "harness": {"slug": "cursor-cli", "name": "Cursor CLI", "vendor": "Cursor", "scaffold_code": null, "repo_url": "https://github.com/getcursor/cursor", "homepage_url": "https://cursor.com", "openrouter_icon_url": "https://cursor.com/apple-touch-icon.png", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-7-opus-medium", "name": "Claude 4.7 Opus (medium)", "vendor": "Anthropic"}, "success_rate": 74.53, "resolved_count": null, "total_count": null, "cost_usd": 2.72490571101738, "input_tokens": 2855520, "output_tokens": 17872, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 32, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "glm-5-2", "name": "GLM 5 2", "vendor": "Zhipu"}, "success_rate": 72.28, "resolved_count": null, "total_count": null, "cost_usd": 6.657531358159516, "input_tokens": 5529735, "output_tokens": 28567, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 33, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-6-high", "name": "GPT-5.6 (high)", "vendor": "OpenAI"}, "success_rate": 72.28, "resolved_count": null, "total_count": null, "cost_usd": 1.5618390533742323, "input_tokens": 2877096, "output_tokens": 20902, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 34, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "qwen3-7-plus-thinking", "name": "Qwen3.7 Plus (thinking)", "vendor": "Qwen"}, "success_rate": 71.54, "resolved_count": null, "total_count": null, "cost_usd": 6.3006588057259885, "input_tokens": 4715248, "output_tokens": 32611, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 35, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-6-xhigh", "name": "GPT-5.6 (xhigh)", "vendor": "OpenAI"}, "success_rate": 70.79, "resolved_count": null, "total_count": null, "cost_usd": 1.2093171048466254, "input_tokens": 6575104, "output_tokens": 30840, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 36, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "deepseek-v4-pro-high", "name": "Deepseek V4 Pro High", "vendor": "DeepSeek"}, "success_rate": 70.04, "resolved_count": null, "total_count": null, "cost_usd": 0.2547256318476481, "input_tokens": 5181244, "output_tokens": 41975, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 37, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "kimi-k2-6", "name": "KIMI K2.6", "vendor": "Moonshot"}, "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, "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"}, {"rank": 38, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "deepseek-v4-flash-0731-max", "name": "Deepseek V4 Flash 0731 Max", "vendor": "DeepSeek"}, "success_rate": 67.79, "resolved_count": null, "total_count": null, "cost_usd": 0.05949917044417178, "input_tokens": 10443571, "output_tokens": 58411, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 39, "harness": {"slug": "cursor-cli", "name": "Cursor CLI", "vendor": "Cursor", "scaffold_code": null, "repo_url": "https://github.com/getcursor/cursor", "homepage_url": "https://cursor.com", "openrouter_icon_url": "https://cursor.com/apple-touch-icon.png", "leaderboard_icon_url": null}, "model": {"slug": "composer-2-5-fast", "name": "Composer 2 5 Fast", "vendor": "Cursor"}, "success_rate": 67.79, "resolved_count": null, "total_count": null, "cost_usd": 0.5573437730061347, "input_tokens": 2153033, "output_tokens": 20146, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 40, "harness": {"slug": "cursor-cli", "name": "Cursor CLI", "vendor": "Cursor", "scaffold_code": null, "repo_url": "https://github.com/getcursor/cursor", "homepage_url": "https://cursor.com", "openrouter_icon_url": "https://cursor.com/apple-touch-icon.png", "leaderboard_icon_url": null}, "model": {"slug": "composer-2-5", "name": "Composer 2 5", "vendor": "Cursor"}, "success_rate": 67.79, "resolved_count": null, "total_count": null, "cost_usd": 0.08505141359918204, "input_tokens": 1872461, "output_tokens": 18453, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 41, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "claude-4-6-sonnet-medium", "name": "Claude 4.6 Sonnet (medium)", "vendor": "Anthropic"}, "success_rate": 67.42, "resolved_count": null, "total_count": null, "cost_usd": 2.0415130214723938, "input_tokens": 4205086, "output_tokens": 40070, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 42, "harness": {"slug": "claude-code", "name": "Claude Code", "vendor": "Anthropic", "scaffold_code": "cc", "repo_url": "https://github.com/anthropics/claude-code", "homepage_url": "https://github.com/anthropics/claude-code", "openrouter_icon_url": "https://claude.ai/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "glm-5-1", "name": "GLM 5 1", "vendor": "Zhipu"}, "success_rate": 67.42, "resolved_count": null, "total_count": null, "cost_usd": 4.282000252842536, "input_tokens": 13139446, "output_tokens": 49883, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 43, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "deepseek-v4-pro-0813-max", "name": "Deepseek V4 Pro 0813 Max", "vendor": "DeepSeek"}, "success_rate": 62.92, "resolved_count": null, "total_count": null, "cost_usd": 0.09081146755368102, "input_tokens": 6378205, "output_tokens": 37873, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 44, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-6-medium", "name": "GPT-5.6 (medium)", "vendor": "OpenAI"}, "success_rate": 62.17, "resolved_count": null, "total_count": null, "cost_usd": 0.44305367719836414, "input_tokens": 2221162, "output_tokens": 11663, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}, {"rank": 45, "harness": {"slug": "codex", "name": "Codex", "vendor": "OpenAI", "scaffold_code": null, "repo_url": "https://github.com/openai/codex", "homepage_url": "https://openai.com/codex", "openrouter_icon_url": "https://openai.com/favicon.ico", "leaderboard_icon_url": null}, "model": {"slug": "gpt-5-6", "name": "GPT-5.6", "vendor": "OpenAI"}, "success_rate": 60.3, "resolved_count": null, "total_count": null, "cost_usd": 1.0868546433537856, "input_tokens": 1731981, "output_tokens": 7689, "latency_ms": null, "temperature": null, "max_turns": null, "context_budget_tokens": 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"}]}}