Skip to content

Benchmark

MMAU

Scores are percentages. Higher is better.

Models and systems measured
14
Scores recorded
21
Sources
3
IQ weight
0.00

Score distribution

72.4%
Mean
71.6%
Median
6.9%
Std dev
63.5%
10th percentile
81.8%
90th percentile
61.6%
Min
61.6%82.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 for chat models, measured over 12 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 systemScore
1Qwen3.5 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.82.2%
2Qwen3.5 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.81.9%
3Qwen3.8 Omni Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.8%
4Qwen3.8 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.81.8%
5Qwen3.5 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.80.4%
6Inkling FP4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.2%
7Inkling Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77%
8Gemini 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.76.9%
9Gemini 2.5 FlashTest-mini· MMAU (audio) data71.8%
10Gemini 2.5 ProTest-mini· MMAU (audio) data71.6%
11Gemini 2.0 FlashTest-mini· MMAU (audio) data70.5%
12Gemini 2.5 ProTest· MMAU (audio) data69.4%
13Gemini 2.5 FlashTest· MMAU (audio) data67.4%
14Gemini 2.0 FlashTest· MMAU (audio) data67%
15Gemini 2.5 Flash-LiteTest-mini· MMAU (audio) data66.2%
16Phi 4 Multimodal InstructTest-mini· MMAU (audio) data65.7%
17Qwen2.5-Omni 7B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.6%
18Muse 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.63.5%
19Phi 4 Multimodal InstructTest· MMAU (audio) data62.8%
20Gemini 2.5 Flash-LiteTest· MMAU (audio) data61.6%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
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.77.2%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats