Benchmark
UniGenBench++ (Chinese Long) - Text
Scores are percentages.
- Models measured
- 26
- Scores recorded
- 26
- Sources
- 1
- IQ weight
- 0.53
Score distribution
- 45.5%
- Mean
- 57.1%
- Median
- 35.8%
- Std dev
- 3%
- 10th percentile
- 91.3%
- 90th percentile
- 0.27%
- Min
This benchmark has a weight of 0.53 for image-generation models, measured over 25 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: UniGenBench++ (CodeGoat24), MIT (licence)