Skip to content

Benchmark

MMEB VisDoc - MMLongBench-page-fixed

Long context benchmarks measure how well models use information in long inputs. Scores are percentages.

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

Score distribution

60.3%
Mean
60.3%
Median
0%
Std dev
60.3%
10th percentile
60.3%
90th percentile
60.3%
Min

Leaderboard

#ModelScore
1Qwen3-VL Embedding 8BMMLongBench-page-fixed· MMEB (TIGER-Lab) data60.3%

Data credits: MMEB Leaderboard (TIGER-Lab), Apache-2.0 (licence)