Skip to content

Benchmark

Exploitbench Mean

Scores are percentages.

Models measured
8
Scores recorded
8
Sources
1
IQ weight
1.48

Score distribution

3.3%
Mean
3.4%
Median
1.3%
Std dev
2.2%
10th percentile
3.7%
90th percentile
2.1%
Min
2.1%6.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.48 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)