Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Generative Performance on HealthBench

0.67Pearson r

RUDE

Updated 21d ago

Evaluation Results

Method	Links
RUDE 2026.05		0.67	0.001	0.66	0.01

SOTA Paper

RUDE

On Predicting the Post-training Potential of Pre-trained LLMs

Dataset

HealthBench

Follow for update

@wizwand_team Discord

Related Benchmarks

Discriminative Evaluation on RuDE base Generative Performance on AdvancedIF Generative Performance on WritingBench Generative Performance on PRBench

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs