Benchmark
AHELM: Air-Bench Foundation - EM
Safety benchmarks examine risks in model behaviour, including how models respond to unsafe requests. Scores are percentages.
- Models measured
- 12
- Scores recorded
- 56
- Sources
- 1
- IQ weight
- 1.10
Score distribution
- 59.3%
- Mean
- 57.5%
- Median
- 11.9%
- Std dev
- 44.3%
- 10th percentile
- 77%
- 90th percentile
- 32.7%
- Min
This benchmark has a weight of 1.10 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.
Leaderboard
| # | Model | Score |
|---|---|---|
| 51 | GPT-4o mini Audio Previewsubject: music_instrument_classification· AHELM (HELM Audio) data | 40.7% |
| 52 | gemini-1.5-pro-001subject: music_instrument_classification· AHELM (HELM Audio) data | 37.6% |
| 53 | GPT-4o Audio Previewsubject: music_instrument_classification· AHELM (HELM Audio) data | 36.9% |
| 54 | gemini-1.5-pro-002subject: music_instrument_classification· AHELM (HELM Audio) data | 36.8% |
| 55 | gemini-1.5-flash-002subject: music_instrument_classification· AHELM (HELM Audio) data | 33.8% |
| 56 | gemini-1.5-flash-001subject: music_instrument_classification· AHELM (HELM Audio) data | 32.7% |
Showing 51–56 of 56 results.