Arcadia MMMU Multiple Choice — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O4 Mini (2025-04-16) | 79.46 |
| 2 | Gemini 2.0 Flash (001) | 66 |
| 3 | Claude 3.7 Sonnet (20250219) | 65.88 |
| 4 | GPT-4o (2024-08-06) | 64.23 |
| 5 | DeepSeek R1 | 56.08 |
| 6 | GPT-4o Mini (2024-07-18) | 55.02 |
| 7 | mistral-small-latest | 54.55 |
| 8 | DeepSeek V3 Chat | 52.18 |
| 9 | Llama 3.2 90B Vision Instruct | 51.83 |
| 10 | Llama 3.3 70B Instruct | 51.12 |
| 11 | O1 Mini (2024-09-12) | 44.39 |
Interactive version: theaggregate.ai/benchmark?slug=arcadia-mmmu-multiple-choice · How the rankings work · Data refreshed daily, snapshot 2026-07-22.