Skip to content

Benchmark

EQ-Bench

Vision benchmarks measure how well models understand images.

Models measured
1
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

1,585.5
Mean
1,586
Median
0.5
Std dev
1,585
10th percentile
1,586
90th percentile
1,585
Min
1,5851,586
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Grok 4.1thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,586
2Grok 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1,585

Data credits: Data by LLM Stats