Skip to content

Benchmark

MMVU

Scores are percentages. Higher is better.

Models measured
12
Scores recorded
14
Sources
2
IQ weight
1.13

Score distribution

75.3%
Mean
75.4%
Median
5.9%
Std dev
67.5%
10th percentile
82.1%
90th percentile
62.7%
Min
62.7%82.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.13 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

#ModelScore
1Qwen3.8 MaxQwen3.8-Max release vision/video table · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.4%
2Kimi K3three-run average · max effort · temp 1.0 · top_p .95· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.1%
3GLM 5.3 Flashsetting not named by the source· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.5%
4GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.5%
5Kimi K2.5setting not named by the source· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.4%
6Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.4%
7Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75.4%
8Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.7%
9Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.3%
10Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.1%
11Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.3%
12Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69%
13Qwen3.5 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.67.5%
14Qwen3.5 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.62.7%

Data credits: Data by LLM Stats · 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.