Benchmark
CharXiv Reasoning Questions - NC
Vision benchmarks measure how well models understand images. Scores are percentages. Higher is better.
- Models measured
- 21
- Scores recorded
- 21
- Sources
- 1
- IQ weight
- 1.22
Score distribution
- 36.5%
- Mean
- 33.6%
- Median
- 12.6%
- Std dev
- 24.6%
- 10th percentile
- 47.8%
- 90th percentile
- 12.1%
- Min
This benchmark has a weight of 1.22 for chat models, measured over 21 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: CharXiv (Wang et al., NeurIPS 2024), Princeton NLP. https://charxiv.github.io