MuseBench - Multi-Select (Overall): leaderboard
Metric: Overall exact-match accuracy (%) on multi-select questions; higher is better. Source: arxiv.org. Saturation forecast: Around 2033. 28 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 28.91 |
| 2 | GPT-5.4 | 25.5 |
| 3 | Qwen 3.5 Plus | 23.21 |
| 4 | Qwen 3.5 397B A17B | 22.71 |
| 5 | InternVL3-8B | 20.3 |
| 6 | Qwen2.5-Omni-7B | 18.18 |
| 7 | Gemini 3.1 Pro (Preview) | 14.88 |
| 8 | InternVL3-78B | 13.53 |
| 9 | Gemma 4 E4B | 9.06 |
| 10 | GLM-4.5V | 8.61 |
| 11 | Grok 4.1 | 8 |
| 12 | Kimi K2.5 | 2.07 |
Interactive version: theaggregate.ai/benchmark?slug=musebench-multi-select-overall · How It Works · Data refreshed daily, snapshot 2026-09-29.