PropensityBench
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Full rankings
1 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  Qwen2.5 32B Instruct | 22.9 |
Frequently asked
Pulled from the PropensityBench dataset · updated daily
What does PropensityBench measure?
PropensityBench is a knowledge benchmark in the BenchGecko catalog. 1 AI models have been tested on it. Scores range from 22.9 to 22.9 out of 100.
Which model leads on PropensityBench?
Qwen2.5 32B Instruct from Alibaba leads PropensityBench with a score of 22.9. The median score across 1 tested models is 22.9.
Is PropensityBench saturated?
No · the top score is 22.9 out of 100 (23%). There is still meaningful room for improvement on PropensityBench.
What makes PropensityBench distinctive?
PropensityBench is a knowledge benchmark with limited overlap to the rest of the catalog · it measures capabilities that are not well-covered by other benchmarks we track.
How often is PropensityBench data refreshed?
BenchGecko pulls updates daily. New model scores on PropensityBench appear as soon as they are published by Epoch AI or the model provider.
Top on PropensityBench
Qwen2.5 32B Instruct · 22.9Compare models
Qwen2.5 32B Instruct vs Qwen2.5 32B InstructMore knowledge benchmarks
Same category · related evaluations