Skip to content

Benchmark

MIABench

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

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

Score distribution

92.7%
Mean
92.7%
Median
0%
Std dev
92.7%
10th percentile
92.7%
90th percentile
92.7%
Min

Leaderboard

#ModelScore
1Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.927%

Data credits: Data by LLM Stats