Skip to content

Benchmark

MMT-Bench

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

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

63.6%
Mean
63.6%
Median
0%
Std dev
63.6%
10th percentile
63.6%
90th percentile
63.6%
Min

Leaderboard

#ModelScore
1DeepSeek VL2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.6%
2Qwen2.5-VL 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.6%

Data credits: Data by LLM Stats