MuseBench - Single-Select (Overall): leaderboard
Metric: Overall chance-adjusted accuracy (%): raw single-select accuracy minus the per-item chance baseline, rescaled so random guessing scores 0 and a correct answer 1; a negative value is worse than chance; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 28 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 Plus | 58.52 |
| 2 | Claude Opus 4.6 | 55.13 |
| 3 | Qwen 3.5 397B A17B | 53.42 |
| 4 | GPT-5.4 | 50.28 |
| 5 | InternVL3-78B | 47.03 |
| 6 | Gemini 3.1 Pro (Preview) | 43.77 |
| 7 | Qwen2.5-Omni-7B | 30.71 |
| 8 | InternVL3-8B | 29.49 |
| 9 | Gemma 4 E4B | 28.67 |
| 10 | Kimi K2.5 | 18.33 |
| 11 | Grok 4.1 | 13.71 |
| 12 | GLM-4.5V | 5.43 |
Interactive version: theaggregate.ai/benchmark?slug=musebench-single-select-overall · How It Works · Data refreshed daily, snapshot 2026-09-29.