Skip to content

Benchmark

LongText-Bench

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

96.6%
Mean
96.6%
Median
0%
Std dev
96.6%
10th percentile
96.6%
90th percentile
96.6%
Min

Leaderboard

#ModelScore
1GLM-Image· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96.6%

Data credits: Data by LLM Stats