Skip to content

Benchmark

MMEB VisDoc - VisRAG

Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages.

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

Score distribution

88.7%
Mean
88.7%
Median
0%
Std dev
88.7%
10th percentile
88.7%
90th percentile
88.7%
Min

Leaderboard

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