AA GDP.pdf - HR - Criterion Pass Rate: leaderboard
Artificial Analysis's implementation of Surge AI's GDP.pdf restricted to its HR 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 | MiMo-V2.6-Pro | 90.13 | #48 |
| 2 | Claude Opus 5 (High) | 89.07 | #16 (Claude Opus 5) |
| 3 | Claude Opus 5 (xHigh) | 87.25 | #16 (Claude Opus 5) |
| 4 | Claude Opus 5 (Max) | 86.96 | #16 (Claude Opus 5) |
| 5 | Claude Opus 5 (Medium) | 86.2 | #16 (Claude Opus 5) |
| 6 | Muse Spark Open (xHigh) | 85.57 | #42 (Muse Spark Open) |
| 7 | GPT-6 Astra (High) | 85.49 | #6 (GPT-6 Astra) |
| 8 | GPT-6 Astra (Medium) | 85.16 | #6 (GPT-6 Astra) |
| 9 | GPT-6 Astra (Low) | 84.66 | #6 (GPT-6 Astra) |
| 10 | Claude Haiku 5.5 (High) | 84.12 | #43 (Claude Haiku 5.5) |
| 11 | Claude Haiku 5.5 (xHigh) | 83.22 | #43 (Claude Haiku 5.5) |
| 12 | GPT-6.1 Sol (High) | 83.07 | #7 (GPT-6.1 Sol) |
| 13 | GPT-6.1 Sol (Low) | 83.07 | #7 (GPT-6.1 Sol) |
| 14 | GPT-6.1 Sol (Medium) | 82.88 | #7 (GPT-6.1 Sol) |
| 15 | Claude Opus 5 (Low) | 82.76 | #16 (Claude Opus 5) |
No result here: #3 Claude Opus 5.5, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=aa-gdp-pdf-hr-criterion-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.