Best AI for Legal Work
Compare AI models for legal work — contract review, case research, compliance drafting and long-document analysis.Rankings combine multiple benchmark scores weighted by relevance to this use case. Updated August 2026.
Why This Matters
Legal Work is one of the most common AI workloads — and the best model depends heavily on the specific task. A model that excels at creative writing may struggle with structured data extraction, and vice versa.
We built this use-case ranking by combining multiple benchmark categories with weights tuned to match real-world usage patterns. For legal work, the score emphasizes the benchmarks that matter most: task accuracy, output quality, and consistency. Speed and cost are factored in but secondary to quality.
All scores are from public independent benchmarks. For a broader view across all tasks, see the overall LLM leaderboard or the expert picks page.
Quick Answer
The best AI models for legal work are:1. Qwen3.7 Max (Alibaba, score: 77.3), 2. GPT-6 Astra (OpenAI, score: 74.8), 3. Claude Fable 5 (Anthropic, score: 74.2).
| # | Model | Provider | Score | Speed | Price (output) |
|---|---|---|---|---|---|
| 1 | Qwen3.7 Max | Alibaba | 77.3 | 203 t/s | $7.5/M |
| 2 | GPT-6 Astra | OpenAI | 74.8 | 82 t/s | $50/M |
| 3 | Claude Fable 5 | Anthropic | 74.2 | 71 t/s | $50/M |
| 4 | Claude Opus 5 | Anthropic | 72.4 | 60 t/s | $25/M |
| 5 | Qwen3.8 Flash Next | Alibaba | 72.3 | 168 t/s | $0.4/M |
| 6 | Gemini 3.1 Pro | 71.4 | 136 t/s | $12/M | |
| 7 | GLM-5.3 Flash | Z.ai | 70.7 | 182 t/s | $0.3/M |
| 8 | Claude Opus 4.8 | Anthropic | 69.6 | 50 t/s | $15/M |
| 9 | GPT-5.6 Sol | OpenAI | 69.0 | 72 t/s | $30/M |
| 10 | DeepSeek V4.1 Flash | DeepSeek | 67.8 | 214 t/s | $1.2/M |
| 11 | Kimi K3 | Moonshot AI | 67.6 | 37 t/s | $15/M |
| 12 | Claude Opus 4.7 | Anthropic | 66.3 | 80 t/s | $15/M |
| 13 | Claude Mythos Preview | Anthropic | 64.6 | 80 t/s | $15/M |
| 14 | Muse Spark 1.1 | Meta | 63.4 | 208 t/s | $4.25/M |
| 15 | Qwen3.6 Plus | Alibaba | 62.7 | 55 t/s | $3/M |