GDP.pdf — leaderboard
Surge AI multimodal reasoning benchmark with professional PDF workflows across finance, healthcare, legal, engineering, insurance, and related domains.
Metric: Strict Pass Rate (%). Source: surgehq.ai. Status: saturation imminent. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 52.8 |
| 2 | GPT-5.6 Sol | 30.7 |
| 3 | GPT-5.5 (xHigh) | 26 |
| 4 | GPT-5.6 Terra | 24.7 |
| 5 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 24 |
| 6 | GPT-5.6 Luna | 22.7 |
| 7 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | 21 |
| 8 | Kimi K3 | 19 |
| 9 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | 18 |
| 10 | Gemini 3.1 Pro (Preview) | 17 |
| 11 | Muse Spark 1.1 | 15 |
| 12 | Gemini 3.5 Flash | 14 |
| 13 | Grok 4.5 (High) | 14 |
| 14 | Kimi K2.6 | 12 |
| 15 | Gemini 3 Flash | 10 |
Interactive version: theaggregate.ai/benchmark?slug=gdp-pdf · How the rankings work · Data refreshed daily, snapshot 2026-07-22.