Official benchmarks map / mmi
Qwen/Qwen3-Omni-30B-A3B-Instruct is ranked first on the mmi leaderboard with 13.54, 16.9% ahead of meta-models/Muse-Glimmer-30B. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | Qwen/Qwen3-Omni-30B-A3B-Instruct | Qwen | 13.54 |
| 2 | meta-models/Muse-Glimmer-30B | meta-models | 11.58 |
| 3 | Qwen/Qwen3.8-27B | Qwen | 11.46 |
mmi is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.
Original board: huggingface.co/datasets/facebook/mmi
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.