Legal Benchmarks - Contract Workflows - Criteria Pass Rate: leaderboard
Legal Benchmarks Contract Workflows: share of applicable lawyer-authored pass/fail criteria satisfied in both of a model's two attempts, graded one criterion at a time by a calibrated GLM 5.3 Flash judge. Shows coverage of the legal requirements even when a whole task fails; %, higher is better. Tables are replaced each monthly cycle.
Metric: Criteria pass rate (%, criteria met in both attempts). Source: www.legalbenchmarks.ai. Saturation forecast: Around February 2027. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 91.7 | #3 |
| 2 | Claude Fable 5.1 | 90.7 | #10 |
| 3 | Claude Opus 5 | 90.1 | #16 |
| 4 | Muse Spark 1.3 | 87.4 | #31 |
| 5 | GPT-6 Astra | 87.1 | #6 |
| 6 | GPT-6.1 Sol | 86.3 | #7 |
| 7 | Claude Sonnet 5.5 | 85.3 | #14 |
| 8 | GPT-5.6 Sol | 84.8 | #22 |
| 9 | GPT-6.1 Terra | 82.9 | #15 |
| 10 | GPT-5.6 Terra | 81.2 | #40 |
| 11 | GPT-5.6 Luna | 80.9 | #79 |
| 12 | MiniMax-M3 | 80.1 | #151 |
| 13 | Claude Sonnet 5 | 80.1 | #65 |
| 14 | Kimi K3 | 78.8 | #35 |
| 15 | DeepSeek V4 Pro | 78.6 | #112 |
Interactive version: theaggregate.ai/benchmark?slug=legal-benchmarks-contract-workflows-criteria-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.