Benchmark
Exploitbench Mean capability
Scores are percentages.
All general benchmarksScores from Epoch AI Benchmarking Hub data.
- 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
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)