Benchmark
GenExam Relaxed - Eng
Scores are percentages.
- Models measured
- 27
- Scores recorded
- 29
- Sources
- 1
- IQ weight
- 0.69
Score distribution
- 58%
- Mean
- 65.5%
- Median
- 31.9%
- Std dev
- 15.4%
- 10th percentile
- 95.9%
- 90th percentile
- 10.2%
- Min
This benchmark has a weight of 0.69 for image-generation models, measured over 26 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: GenExam (OpenGVLab), MIT (licence)