Skip to content

Benchmark

Exploitbench Mean capability

Scores are percentages.

Models measured
8
Scores recorded
8
Sources
1
IQ weight
1.50

Score distribution

23.4%
Mean
23.6%
Median
10.3%
Std dev
13.7%
10th percentile
26.5%
90th percentile
13.3%
Min
13.3%47.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.50 for chat models, measured over 8 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: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)