Legal Benchmarks - Contract Workflows - Form: leaderboard
Legal Benchmarks Contract Workflows: Form is the share of applicable binary presentation checks (output usable as delivered) passed in both attempts, judged by GLM 5.3 Flash with a separate checklist that has no lawyer-labelled accuracy measurement. It does not affect the site's ranking; %, higher is better.
Metric: Form (%, binary form checks passed 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 | 93.9 | #3 |
| 2 | GPT-6 Astra | 91.9 | #6 |
| 3 | Claude Sonnet 5.5 | 91.1 | #14 |
| 4 | Claude Opus 5 | 90.8 | #16 |
| 5 | GPT-6.1 Sol | 90.8 | #7 |
| 6 | Claude Fable 5.1 | 89.7 | #10 |
| 7 | GPT-5.6 Sol | 89.2 | #22 |
| 8 | DeepSeek V4 Pro | 88.3 | #112 |
| 9 | Muse Spark 1.3 | 87.8 | #31 |
| 10 | Claude Sonnet 5 | 86.9 | #65 |
| 11 | GPT-5.6 Luna | 86.1 | #79 |
| 12 | GPT-5.6 Terra | 86 | #40 |
| 13 | Kimi K3 | 84.7 | #35 |
| 14 | MiniMax-M3 | 83.4 | #151 |
| 15 | Claude Haiku 5.5 | 83.1 | #43 |
Interactive version: theaggregate.ai/benchmark?slug=legal-benchmarks-contract-workflows-form · How It Works · Data refreshed daily, snapshot 2026-11-05.