Benchmark
AHELM: Fairness - Mean win rate
Scores are percentages. Higher is better.
- Models measured
- 12
- Scores recorded
- 12
- Sources
- 1
- IQ weight
- 0.82
Score distribution
- 44.8%
- Mean
- 53.1%
- Median
- 26.4%
- Std dev
- 18.8%
- 10th percentile
- 75%
- 90th percentile
- 3.1%
- Min
This benchmark has a weight of 0.82 for chat models, measured over 9 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.