GDP.pdf: leaderboard
Surge AI multimodal document-reasoning benchmark over native professional PDF pages containing visually structured layouts, tables, charts, and forms across finance, healthcare, legal, engineering, insurance, and related domains.
Metric: Strict Pass Rate (%). Source: surgehq.ai. Status: saturation imminent. 41 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 30.7 |
| 2 | Claude Fable 5 | 29.8 |
| 3 | Claude Fable 5 (Adaptive Reasoning, Max Effort) | 29.8 |
| 4 | Claude Fable 5.1 | 29.6 |
| 5 | Muse Spark 1.3 (xHigh) | 27.6 |
| 6 | Muse Spark 1.3 | 27.6 |
| 7 | GPT-5.5 (xHigh) | 26 |
| 8 | GPT-5.6 Terra | 24.7 |
| 9 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 24 |
| 10 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 24 |
| 11 | Gemini 3.7 Flash (High) | 23.8 |
| 12 | Gemini 3.8 Flash | 23.4 |
| 13 | Qwen 3.8 Max | 23.2 |
| 14 | Gemini 3.8 Flash (High) | 23.2 |
| 15 | GPT-5.6 Luna | 22.7 |
Interactive version: theaggregate.ai/benchmark?slug=gdp-pdf · How It Works · Data refreshed daily, snapshot 2026-09-08.