WildVision-Bench — leaderboard
Metric: Overall Reward. Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.7 Sonnet | 60.6 |
| 2 | GPT-4.1 (2025-04-14) | 58.7 |
| 3 | Claude 3.5 Sonnet (20241022) | 53.2 |
| 4 | InternVL3-38B | 45.2 |
| 5 | InternVL2.5-78B | 42.4 |
| 6 | Grok 2 (1212) | 40 |
| 7 | InternVL3-78B | 39.6 |
| 8 | InternVL3-8B | 36.5 |
| 9 | Gemini 2.0 Flash | 35.5 |
| 10 | Gemini 2.5 Flash | 32.4 |
| 11 | Llama 4 Scout Instruct | 31.5 |
| 12 | Pixtral-12B | 11.8 |
| 13 | Llama 3.2 11B Instruct | 1.9 |
Interactive version: aibenchmarks.dev/benchmark?slug=wildvision-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-13.