AA GDP.pdf - Legal - Criterion Pass Rate: leaderboard
Artificial Analysis's implementation of Surge AI's GDP.pdf restricted to its Legal domain: the mean share of task-specific atomic criteria satisfied on professional tasks over long PDF documents. Reported 0-100 (%); higher is better. A criterion pass rate, not the all-criteria pass rate shown on the AA GDP.pdf board.
Metric: Criterion Pass Rate (%). Source: artificialanalysis.ai. Saturation forecast: Around February 2027. 242 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3.1 Pro | 89.44 | #17 |
| 2 | Muse Wonder (Max) | 88.03 | #18 (Muse Wonder) |
| 3 | Muse Spark Open (xHigh) | 87.81 | #42 (Muse Spark Open) |
| 4 | Muse Wonder Full (Max) | 87.8 | #12 (Muse Wonder Full) |
| 5 | mistral-large-4-oss (High) | 87.34 | #60 (mistral-large-4-oss) |
| 6 | DeepSeek V4.1 Flash (Max) | 87.28 | #37 (DeepSeek V4.1 Flash) |
| 7 | Mistral Large 4 | 86.43 | #106 |
| 8 | GPT-5.6 Terra (Max) | 86 | #40 (GPT-5.6 Terra) |
| 9 | Kimi K3 (Max) | 85.99 | #35 (Kimi K3) |
| 10 | GPT-6.1 Sol (Max) | 85.86 | #7 (GPT-6.1 Sol) |
| 11 | GPT-6 Astra (Max) | 85.11 | #6 (GPT-6 Astra) |
| 12 | Step 5 Preview | 84.93 | #53 |
| 13 | Muse Spark 1.1 (xHigh) | 84.9 | #55 (Muse Spark 1.1) |
| 14 | Qwen 3.8 Max | 84.84 | #34 |
| 15 | GLM-5.3 Flash | 84.82 | #77 |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=aa-gdp-pdf-legal-criterion-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.