MapVerse - Boolean: leaderboard
Metric: Accuracy (%) on MapVerse's 1,982 human-authored yes/no questions over real-world maps, zero-shot image plus question; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 72.2 | #643 |
| 2 | Llama 3.2 11B Instruct | 69.1 | #1112 |
| 3 | InternVL3-8B | 69 | #606 |
| 4 | Mistral Small 3.2 | 67.5 | #587 |
| 5 | aya-vision-8B | 67.3 | #1094 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=mapverse-boolean · How It Works · Data refreshed daily, snapshot 2026-10-11.