Skip to content

Benchmark

MMBench-V1.1

Vision benchmarks measure how well models understand images. Scores are percentages.

Models measured
12
Scores recorded
14
Sources
1
IQ weight
2.01

Score distribution

88.8%
Mean
90.6%
Median
4.1%
Std dev
81.8%
10th percentile
92.8%
90th percentile
79.2%
Min
79.2%92.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.01 for chat models, measured over 11 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.8%
2Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.8%
3Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.6%
4Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.3%
5Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.5%
6Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.90.8%
7Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.90.6%
8Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.89.9%
9qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.88.9%
10Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.87.5%
11qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.87%
12Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.85%
13Qwen2.5-Omni 7B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.8%
14DeepSeek VL2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.2%

Data credits: Data by LLM Stats