Benchmark
MAEB(v1, audio-only)
Scores are percentages.
- Models measured
- 8
- Scores recorded
- 8
- Sources
- 1
- IQ weight
- 0.49
Score distribution
- 46.7%
- Mean
- 47.8%
- Median
- 2.5%
- Std dev
- 44%
- 10th percentile
- 49.7%
- 90th percentile
- 43.6%
- Min
This benchmark has a weight of 0.49 for speech models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.