DocVQA 2026 - Maps: leaderboard
DocVQA 2026 accuracy on maps documents under the published high-thinking baseline protocol.
Metric: Accuracy (%, high thinking). Source: huggingface.co. Saturation forecast: Around 2031. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 (High) | 20 | #115 (GPT-5.2) |
| 2 | GPT-5 Mini (High) | 10 | #193 (GPT-5 Mini) |
| 3 | Gemini 3 Pro (Preview) (High) | 0 | #71 (Gemini 3 Pro (Preview)) |
| 4 | Gemini 3 Flash (Preview) (High) | 0 | #90 (Gemini 3 Flash (Preview)) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=docvqa-2026-maps · How It Works · Data refreshed daily, snapshot 2026-11-05.