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. Source: surgehq.ai. Saturation forecast: Around 2030. 6 models tracked.

Top models

#ModelScoreOverall rank
1GPT-6.1 Sol (Max)35#7 (GPT-6.1 Sol)
2GPT-6 Astra (Max)34.2#6 (GPT-6 Astra)
3Muse Wonder Full (Max)33.2#10 (Muse Wonder Full)
4Muse Wonder (Max)30.8#14 (Muse Wonder)
5GPT-5.6 Sol (Max)30.7#18 (GPT-5.6 Sol)

No result here: #4 Claude Opus 5.5, #8 Gemini 4 Argon, #9 Claude Fable 5.1.

Interactive version: theaggregate.ai/benchmark?slug=gdp-pdf · How It Works · Data refreshed daily, snapshot 2026-10-23.