DrawingVQA: leaderboard
Metric: Accuracy (%; all 92 expert-curated questions on 33 Issued for Construction drawings, multiple choice and open-ended). Source: arxiv.org. Saturation forecast: Around March 2027. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 77.2 |
| 2 | Gemini 2.5 Pro | 71.7 |
| 3 | Gemini 2.5 Flash | 66.3 |
| 4 | O3 (2025-04-16) | 58.7 |
| 5 | Qwen 3 VL 32B Instruct | 58.7 |
| 6 | Claude Sonnet 4.5 | 57.6 |
| 7 | Claude Haiku 4.5 | 54.3 |
| 8 | Llama 4 Scout Instruct | 53.3 |
| 9 | Qwen 3 VL 8B Instruct | 53.3 |
| 10 | InternVL3.5-8B | 50 |
| 11 | GPT-4o (2024-08-06) | 48.9 |
| 12 | Qwen 3 VL 30B A3B Instruct | 47.8 |
| 13 | Phi-4 Multimodal Instruct | 40.2 |
| 14 | Llama 3.2 11B Instruct | 39.1 |
Interactive version: theaggregate.ai/benchmark?slug=drawingvqa · How It Works · Data refreshed daily, snapshot 2026-09-29.