LegalBench
Evaluating language models on a wide range of open source legal reasoning tasks.
111rows
scoreprimary metric
2026-05-28sampled
Metadata
Metrics
Score, Std. error (lower is better), Latency (lower is better), Cost per test (lower is better)
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro Preview | 87.398% |  Gemini 3.1 Pro Preview google-gemini-3.1-pro-preview | Imported | 2026-05-28 |
| 2 | Gemini 3 Pro Preview | 87.025% | Gemini 3 google-gemini-3 | Imported | 2026-05-28 |
| 3 | Gemini 3 Flash Preview | 86.858% | Gemini 3 Flash Preview google-gemini-3-flash-preview | Imported | 2026-05-28 |
| 4 | GPT 5.5 | 86.515% |  GPT-5.5 openai-gpt-5.5 | Imported | 2026-05-28 |
| 5 | GPT 5.4 2026-03-05 | 86.044% | GPT-5.4 openai-gpt-5.4 | Imported | 2026-05-28 |
| 6 | GPT 5.2025-08-07 | 86.023% | GPT-5 openai-gpt-5 | Imported | 2026-05-28 |
| 7 | GPT 5.1 2025-11-13 | 85.683% | GPT-5.1 openai-gpt-5.1 | Imported | 2026-05-28 |
| 8 | Claude Opus 4.6 Thinking | 85.301% |  Claude Opus 4.6 anthropic-claude-opus-4.6 | Imported | 2026-05-28 |
| 9 | Claude Opus 4.7 | 85.251% | Claude Opus 4.7 anthropic-claude-opus-4.7 | Imported | 2026-05-28 |
| 10 | Qwen 3.5 Plus Thinking | 85.104% | — | Imported | 2026-05-28 |
| 11 | Qwen 3.7 Max | 84.913% |  Qwen3.7 Max qwen-qwen3.7-max | Imported | 2026-05-28 |
| 12 | Kimi K2.6 Thinking | 84.738% | MoonshotAI: Kimi K2.6 moonshotai-kimi-k2.6 | Imported | 2026-05-28 |
| 13 | Claude Opus 4.5 20251101 Thinking | 84.604% | Claude Opus 4.5 anthropic-claude-opus-4.5 | Imported | 2026-05-28 |
| 14 | Grok 4.3 | 84.458% | Grok 4.3 x-ai-grok-4.3 | Imported | 2026-05-28 |
| 15 | GLM 5.1 Thinking | 84.394% | GLM 5.1 z-ai-glm-5.1 | Imported | 2026-05-28 |
| 16 | Gemini 2.5 Pro Exp 03 25 | 84.322% | — | Imported | 2026-05-28 |
| 17 | Qwen 3.5 Flash | 84.276% | Qwen3.5-Flash qwen-qwen3.5-flash-02-23 | Imported | 2026-05-28 |
| 18 | Qwen 3.6 Plus | 84.233% | Qwen3.6 Plus qwen-qwen3.6-plus | Imported | 2026-05-28 |
| 19 | Muse Spark | 84.217% | — | Imported | 2026-05-28 |
| 20 | Claude Sonnet 4.5 20250929 Thinking | 84.084% | Claude Sonnet 4.5 anthropic-claude-sonnet-4.5 | Imported | 2026-05-28 |
| 21 | GLM 5 Thinking | 84.059% | GLM 5 z-ai-glm-5 | Imported | 2026-05-28 |
| 22 | MiniMax M2.7 | 83.98% |  MiniMax M2.7 minimax-minimax-m2.7 | Imported | 2026-05-28 |
| 23 | Gemini 2.5 Flash Preview 04 17 | 83.796% | — | Imported | 2026-05-28 |
| 24 | Gemini 3.1 Flash Lite Preview | 83.764% | Gemini 3.1 Flash Lite Preview google-gemini-3.1-flash-lite-preview | Imported | 2026-05-28 |
| 25 | O3 2025-04-16 | 83.761% | o3 openai-o3 | Imported | 2026-05-28 |
| 26 | Gemini 3.5 Flash | 83.602% | Gemini 3.5 Flash google-gemini-3.5-flash | Imported | 2026-05-28 |
| 27 | Claude Opus 4.8 | 83.568% | Claude Opus 4.8 anthropic-claude-opus-4.8 | Imported | 2026-05-28 |
| 28 | Claude Opus 4.1 20250805 | 83.458% | Claude Opus 4.1 anthropic-claude-opus-4.1 | Imported | 2026-05-28 |
| 29 | GLM 4.7 | 83.358% | GLM 4.7 z-ai-glm-4.7 | Imported | 2026-05-28 |
| 30 | Grok 4.0709 | 83.192% | Grok 4 x-ai-grok-4 | Imported | 2026-05-28 |
| 31 | Grok 3 Mini Fast High Reasoning | 83.143% | — | Imported | 2026-05-28 |
| 32 | GPT 4.1 2025-04-14 | 83.1% | GPT-4.1 openai-gpt-4.1 | Imported | 2026-05-28 |
| 33 | Claude Opus 4.20250514 | 83.071% | Claude Opus 4 anthropic-claude-opus-4 | Imported | 2026-05-28 |
| 34 | Claude Sonnet 4.20250514 | 82.954% | Claude Sonnet 4 anthropic-claude-sonnet-4 | Imported | 2026-05-28 |
| 35 | Claude Opus 4.5 20251101 | 82.837% | Claude Opus 4.5 anthropic-claude-opus-4.5 | Imported | 2026-05-28 |
| 36 | GPT 5.2 2025-12-11 | 82.764% | GPT-5.2 openai-gpt-5.2 | Imported | 2026-05-28 |
| 37 | Gemini 2.5 Flash Preview 09 2025 Thinking | 82.625% | — | Imported | 2026-05-28 |
| 38 | Grok 3 | 82.595% | Grok 3 xaigrok-3 | Imported | 2026-05-28 |
| 39 | Claude 3 7 Sonnet 20250219 Thinking | 82.519% | — | Imported | 2026-05-28 |
| 40 | Gemini 2.5 Flash Preview 09 2025 | 82.486% | — | Imported | 2026-05-28 |
| 41 | Grok 4.1 Fast Reasoning | 82.451% | Grok 4.1 Fast x-ai-grok-4.1-fast | Imported | 2026-05-28 |
| 42 | GPT 4O 2024-11-20 | 82.214% | GPT-4o (2024-11-20) openai-gpt-4o-2024-11-20 | Imported | 2026-05-28 |
| 43 | Claude Sonnet 4.6 | 82.12% | Claude Sonnet 4.6 anthropic-claude-sonnet-4.6 | Imported | 2026-05-28 |
| 44 | Claude Sonnet 4.20250514 Thinking | 82.065% | — | Imported | 2026-05-28 |
| 45 | Gemini 2.5 Flash Lite Preview 09 2025 Thinking | 82.044% | — | Imported | 2026-05-28 |
| 46 | Grok 3 Mini Fast Low Reasoning | 81.925% | — | Imported | 2026-05-28 |
| 47 | Qwen 3 Max | 81.861% | Qwen3 Max qwen-qwen3-max | Imported | 2026-05-28 |
| 48 | GPT 5 Mini 2025-08-07 | 81.77% | GPT-5 Mini openai-gpt-5-mini | Imported | 2026-05-28 |
| 49 | Kimi K2 Instruct | 81.454% | MoonshotAI: Kimi K2 0711 moonshotai-kimi-k2 | Imported | 2026-05-28 |
| 50 | Claude Haiku 4.5 20251001 Thinking | 81.238% | Claude Haiku 4.5 anthropic-claude-haiku-4.5 | Imported | 2026-05-28 |
| 51 | DeepSeek V3 | 80.762% |  DeepSeek V3 deepseek-deepseek-chat | Imported | 2026-05-28 |
| 52 | Grok 4 Fast Reasoning | 80.601% | Grok 4 Fast x-ai-grok-4-fast | Imported | 2026-05-28 |
| 53 | GPT 4 Turbo | 80.462% | GPT-4 Turbo openai-gpt-4-turbo | Imported | 2026-05-28 |
| 54 | O1 2024-12-17 | 80.393% | o1 openai-o1 | Imported | 2026-05-28 |
| 55 | Qwen 3 Max Preview | 80.333% | — | Imported | 2026-05-28 |
| 56 | DeepSeek V4 Pro | 80.323% | DeepSeek V4 Pro deepseek-deepseek-v4-pro | Imported | 2026-05-28 |
| 57 | Kimi K2 Thinking | 80.201% | MoonshotAI: Kimi K2 Thinking moonshotai-kimi-k2-thinking | Imported | 2026-05-28 |
| 58 | Qwen 3 235B A22b | 80.179% | Qwen3 235B A22B qwen-qwen3-235b-a22b | Imported | 2026-05-28 |
| 59 | GPT 4O 2024-08-06 | 80.12% | GPT-4o (2024-08-06) openai-gpt-4o-2024-08-06 | Imported | 2026-05-28 |
| 60 | Claude 3 7 Sonnet 20250219 | 80.001% | Claude 3.7 Sonnet anthropic-claude-3.7-sonnet | Imported | 2026-05-28 |
| 61 | MiniMax M2.5 Lightning | 79.963% | — | Imported | 2026-05-28 |
| 62 | Command A 03 2025 | 79.697% | Command A cohere-command-a | Imported | 2026-05-28 |
| 63 | GLM 4.6 | 79.608% | GLM 4.6 z-ai-glm-4.6 | Imported | 2026-05-28 |
| 64 | Qwen 2.5 72B Instruct Turbo | 79.403% | — | Imported | 2026-05-28 |
| 65 | O4 Mini 2025-04-16 | 79.185% | o4 Mini openai-o4-mini | Imported | 2026-05-28 |
| 66 | Mistral Large 2512 | 79.138% |  Mistral: Mistral Large 3 2512 mistralai-mistral-large-2512 | Imported | 2026-05-28 |
| 67 | Grok 4.1 Fast Non Reasoning | 79.113% | Grok 4.1 Fast x-ai-grok-4.1-fast | Imported | 2026-05-28 |
| 68 | Gemini 2.5 Flash Lite Preview 09 2025 | 79.008% | Gemini 2.5 Flash Lite Preview 09-2025 google-gemini-2.5-flash-lite-preview-09-2025 | Imported | 2026-05-28 |
| 69 | Grok 4 Fast Non Reasoning | 78.396% | Grok 4 Fast x-ai-grok-4-fast | Imported | 2026-05-28 |
| 70 | Gemini 2.0 Flash 001 | 78.364% | Gemini 2.0 Flash google-gemini-2.0-flash | Imported | 2026-05-28 |
| 71 | GPT 4.1 Mini 2025-04-14 | 78.044% | GPT-4.1 Mini openai-gpt-4.1-mini | Imported | 2026-05-28 |
| 72 | GPT 5.4 Nano 2026-03-17 | 77.92% | GPT-5.4 Nano openai-gpt-5.4-nano | Imported | 2026-05-28 |
| 73 | Llama4 Maverick Instruct Basic | 77.812% | — | Imported | 2026-05-28 |
| 74 | Grok 4.20 0309 Reasoning | 77.738% | Grok 4.20 x-ai-grok-4.20 | Imported | 2026-05-28 |
| 75 | DeepSeek V3 0324 | 77.727% | DeepSeek V3 0324 deepseek-deepseek-chat-v3-0324 | Imported | 2026-05-28 |
| 76 | Llama 3.3 70B Instruct Turbo | 77.18% | — | Imported | 2026-05-28 |
| 77 | DeepSeek V3P2 Thinking | 76.076% | — | Imported | 2026-05-28 |
| 78 | GPT Oss 120B | 75.938% | gpt-oss-120b openai-gpt-oss-120b | Imported | 2026-05-28 |
| 79 | GLM 4.5 | 75.627% | GLM 4.5 z-ai-glm-4.5 | Imported | 2026-05-28 |
| 80 | MiniMax M2.1 | 75.448% | MiniMax M2.1 minimax-minimax-m2.1 | Imported | 2026-05-28 |
| 81 | Jamba 1.5 Large | 74.16% | — | Imported | 2026-05-28 |
| 82 | Llama 4 Scout 17B 16E Instruct | 72.036% |  Llama 4 Scout meta-llama-llama-4-scout | Imported | 2026-05-28 |
| 83 | Jamba Large 1.6 | 71.962% | — | Imported | 2026-05-28 |
| 84 | O3 Mini 2025-01-31 | 71.539% | o3-mini openai-o3-mini | Imported | 2026-05-28 |
| 85 | GPT Oss 20B | 70.849% | gpt-oss-20b openai-gpt-oss-20b | Imported | 2026-05-28 |
| 86 | Claude 3 5 Haiku 20241022 | 70.331% | — | Imported | 2026-05-28 |
| 87 | Gemini 1.0 Pro 002 | 70.247% | — | Imported | 2026-05-28 |
| 88 | Jamba Mini 1.6 | 69.726% | — | Imported | 2026-05-28 |
| 89 | Qwen 2.5 7B Instruct Turbo | 69.559% | — | Imported | 2026-05-28 |
| 90 | Mistral Small 2503 | 69.157% | — | Imported | 2026-05-28 |
| 91 | Gemini 1.5 Pro 002 | 69.08% | — | Imported | 2026-05-28 |
| 92 | Command R Plus | 68.287% | — | Imported | 2026-05-28 |
| 93 | Gemma 2 9B It | 68.138% | — | Imported | 2026-05-28 |
| 94 | Gemma 2 27B It | 67.978% | Gemma 2 27B google-gemma-2-27b-it | Imported | 2026-05-28 |
| 95 | DeepSeek R1 | 67.323% | R1 deepseek-r1 | Imported | 2026-05-28 |
| 96 | Jamba 1.5 Mini | 66.616% | — | Imported | 2026-05-28 |
| 97 | DeepSeek V3P2 | 65.962% | — | Imported | 2026-05-28 |
| 98 | GPT 3.5 Turbo | 64.372% | GPT-3.5 Turbo openai-gpt-3.5-turbo | Imported | 2026-05-28 |
| 99 | Gemini 1.5 Flash 002 | 63.238% | — | Imported | 2026-05-28 |
| 100 | Llama 2 70B Hf | 62.434% | — | Imported | 2026-05-28 |
| 101 | Mistral Medium 2505 | 61.979% | — | Imported | 2026-05-28 |
| 102 | Command A Plus 05 2026 | 61.422% | — | Imported | 2026-05-28 |
| 103 | GPT 4.1 Nano 2025-04-14 | 61.056% | GPT-4.1 Nano openai-gpt-4.1-nano | Imported | 2026-05-28 |
| 104 | Mixtral 8x7B V0.1 | 55.836% | — | Imported | 2026-05-28 |
| 105 | Magistral Medium 2509 | 54.767% | — | Imported | 2026-05-28 |
| 106 | Mistral 7B V0.1 | 53.77% | — | Imported | 2026-05-28 |
| 107 | Llama 2 13B | 53.696% | — | Imported | 2026-05-28 |
| 108 | Llama 2 7B | 51.869% | — | Imported | 2026-05-28 |
| 109 | GPT 5 Nano 2025-08-07 | 50.129% | GPT-5 Nano openai-gpt-5-nano | Imported | 2026-05-28 |
| 110 | Magistral Small 2509 | 40.023% | — | Imported | 2026-05-28 |
| 111 | Command R | 32.965% | Command R (08-2024) cohere-command-r-08-2024 | Imported | 2026-05-28 |
No matching rows.