An LLM leaderboard with rankings of model performance on legal-related queries and prompts submitted and scored by legal professionals. Compare LLM model performance, confidence intervals, pricing, and capabilities across top legal AI software—helping you determine which AI is best for legal research, contract review, workflow automation and other legal tasks.
| Rank | Provider | Score | Model ranks | Price $/M | Context |
|---|---|---|---|---|---|
1 | OpenAI 9 ranked models · Top model: GPT-6.1 Sol Best rank 1Avg score 1067 | 1136±36 | 1 - 19 | $0.20-$10.00 / $0.75-$50.00 input / output | 1.1M |
2 | Google 8 ranked models · Top model: Gemini 3.8 Flash Best rank 2Avg score 1067 | 1095±21 | 2 - 28 | $0.25-$2.00 / $1.50-$12.00 input / output | 1M |
3 | Anthropic 11 ranked models · Top model: Claude Fable 5.1 Best rank 7Avg score 1039 | 1073±11 | 7 - 38 | $0.50-$10.00 / $2.50-$50.00 input / output | 1M |
4 | Alibaba 7 ranked models · Top model: Qwen3.7 Max Best rank 21Avg score 1026 | 1042±9 | 21 - 44 | $0.15-$2.50 / $0.47-$12.00 input / output | 1M |
5 | Xiaomi 4 ranked models · Top model: Mimo V2.6 Flash Best rank 26Avg score 1004 | 1034±27 | 26 - 55 | $0.14-$0.44 / $0.28-$0.87 input / output | 1M |
6 | xAI 7 ranked models · Top model: Grok-4.20 Multi-Agent Best rank 30Avg score 953 | 1028±10 | 30 - 76 | $2.00-$4.00 / $5.00-$12.00 input / output | 2M |
7 | Z.ai 7 ranked models · Top model: GLM 5.3 Best rank 37Avg score 993 | 1018±20 | 37 - 61 | $0.15-$1.40 / $0.50-$4.40 input / output | 1M |
8 | Meta 4 ranked models · Top model: Muse Spark 1.2 Best rank 39Avg score 1010 | 1014±23 | 39 - 42 | $1.25-$4.00 / $4.25-$20.00 input / output | 1M |
9 | Moonshot AI 3 ranked models · Top model: Kimi K3 Best rank 43Avg score 993 | 1007±11 | 43 - 58 | $0.60-$3.00 / $3.00-$15.00 input / output | 1M |
10 | DeepSeek 6 ranked models · Top model: DeepSeek V4 Pro 0813 Best rank 50Avg score 962 | 999±18 | 50 - 70 | $0.14-$1.32 / $0.28-$3.96 input / output | 1M |
11 | Thinkingmachines 1 ranked model · Top model: Inkling Best rank 59Avg score 966 | 966±12 | 59 | $1.00 / $4.05 input / output | 256K |
12 | Mistral 3 ranked models · Top model: Mistral Medium 3.5 Best rank 62Avg score 915 | 961±35 | 62 - 75 | $0.20-$1.50 / $0.20-$7.50 input / output | 262K |
13 | MiniMax 5 ranked models · Top model: Minimax M3 Best rank 64Avg score 930 | 953±12 | 64 - 72 | $0.30-$0.60 / $1.20-$2.40 input / output | 512K |
14 | NVIDIA 1 ranked model · Top model: Nemotron 3 Super Best rank 74Avg score 868 | 868±13 | 74 | $0.15 / $0.65 input / output | 256K |