Creation-MMBench — leaderboard
Metric: Overall Reward. Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 6.61 |
| 2 | GPT-4.1 (2025-04-14) | 5.61 |
| 3 | InternVL3-78B | -6.87 |
| 4 | Grok 2 (1212) | -8.86 |
| 5 | Gemini 2.0 Flash | -8.9 |
| 6 | InternVL3-38B | -8.99 |
| 7 | Claude 3.7 Sonnet | -11.28 |
| 8 | InternVL3-8B | -14 |
| 9 | Claude 3.5 Sonnet (20241022) | -15.46 |
| 10 | InternVL2.5-78B | -16.44 |
| 11 | Llama 4 Scout Instruct | -16.44 |
| 12 | Pixtral-12B | -21.45 |
| 13 | Llama 3.2 11B Instruct | -48.23 |
Interactive version: aibenchmarks.dev/benchmark?slug=creation-mmbench · How the rankings work · Data refreshed daily, snapshot 2026-07-13.