Skip to content

Benchmark

MMBench-Video

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

1.9%
Mean
2%
Median
0.1%
Std dev
1.8%
10th percentile
2%
90th percentile
1.8%
Min
1.8%2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen2.5 VL 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim2%
2Qwen2.5-VL 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1.8%

Data credits: Data by LLM Stats