AA GDP.pdf - Construction - Criterion Pass Rate: leaderboard
Artificial Analysis's implementation of Surge AI's GDP.pdf restricted to its Construction 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 January 2028. 242 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol (High) | 84.94 | #7 (GPT-6.1 Sol) |
| 2 | GPT-6 Astra (High) | 84.51 | #6 (GPT-6 Astra) |
| 3 | GPT-6.1 Sol (Medium) | 84.45 | #7 (GPT-6.1 Sol) |
| 4 | GPT-6 Astra (Max) | 82.9 | #6 (GPT-6 Astra) |
| 5 | GPT-6.1 Sol (Max) | 82.68 | #7 (GPT-6.1 Sol) |
| 6 | GPT-6.1 Sol (xHigh) | 82.36 | #7 (GPT-6.1 Sol) |
| 7 | GPT-6 Astra (xHigh) | 81.47 | #6 (GPT-6 Astra) |
| 8 | GPT-6 Astra (Low) | 78.97 | #6 (GPT-6 Astra) |
| 9 | GPT-6 Astra (Medium) | 78.71 | #6 (GPT-6 Astra) |
| 10 | GPT-6.1 Terra (xHigh) | 78.71 | #15 (GPT-6.1 Terra) |
| 11 | GPT-6.1 Sol (Low) | 77.63 | #7 (GPT-6.1 Sol) |
| 12 | Gemini 4 Carbon (High) | 76.92 | #1 (Gemini 4 Carbon) |
| 13 | GPT-6.1 Terra (Max) | 76.68 | #15 (GPT-6.1 Terra) |
| 14 | GPT-6 Sol (Medium) | 76.26 | #19 (GPT-6 Sol) |
| 15 | Muse Wonder Full (Max) | 75.97 | #12 (Muse Wonder Full) |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=aa-gdp-pdf-construction-criterion-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.