Benchmark
MMSU
Scores are percentages. Higher is better.
- Models and systems measured
- 11
- Scores recorded
- 12
- Sources
- 2
- IQ weight
- 0.67
Score distribution
- 66.4%
- Mean
- 72.2%
- Median
- 16%
- Std dev
- 45%
- 10th percentile
- 83%
- 90th percentile
- 35.5%
- Min
This benchmark has a weight of 0.67 for chat models, measured over 9 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | Gemini 3.8 FlashQwen3.8 Omni Flash 官方发布表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83.3% |
| 2 | Qwen3.5 Omni PlusQwen3.8 Omni Flash 官方发布表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83% |
| 3 | Qwen3.5 Omni PlusQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 82.8% |
| 4 | Qwen3.8 Omni FlashQwen3.8 Omni Flash 官方发布表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 82.1% |
| 5 | Qwen3.5 Omni FlashQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 72.2% |
| 6 | Gemini 1.5 Pro· MMSU data | 60.7% |
| 7 | Qwen2.5-Omni 7B· MMSU data | 60.6% |
| 8 | Muse Spark 1.2Qwen3.8 Omni Flash 官方发布表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.9% |
| 9 | Gemini 2.0 Flash· MMSU data | 51% |
| 10 | Phi 4 Multimodal Instruct· MMSU data | 45% |
| 11 | GLM-4-Voice· MMSU data | 35.5% |
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Seed-2.0-LiteQwen3.8 Omni Flash 官方发布表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 80.2% |