Skip to content

Benchmark

EQ-Bench 4

Vision benchmarks measure how well models understand images.

Models measured
32
Scores recorded
32
Sources
1
IQ weight
1.87

Score distribution

1,200
Mean
1,212.1
Median
95.7
Std dev
1,064.9
10th percentile
1,319.2
90th percentile
983.1
Min
983.11,364.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.87 for chat models, measured over 32 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Data credits: EQ-Bench (Samuel J. Paech) — cite paech2023eqbench