Skip to content

Benchmark

MMEB Image - I-RET

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

80.2%
Mean
80.2%
Median
0%
Std dev
80.2%
10th percentile
80.2%
90th percentile
80.2%
Min

Leaderboard

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