Benchmark
UniGenBench++ (Chinese Long) - Pronoun Reference
Scores are percentages.
- Models measured
- 26
- Scores recorded
- 26
- Sources
- 1
- IQ weight
- 2.24
Score distribution
- 87.3%
- Mean
- 92.5%
- Median
- 18.9%
- Std dev
- 83.7%
- 10th percentile
- 97.6%
- 90th percentile
- 0.79%
- Min
This benchmark has a weight of 2.24 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)