Our new X account is live! Follow @wizwand_team for updates

Home/Benchmarks

Big-Bench Hard Reasoning on BBH

45.6Accuracy

MoE + L_ERC

Updated 4d ago

Evaluation Results

Method	Links
MoE + L_ERC 2025.12		45.6
MoE 2025.12		44.3

SOTA Paper

MoE + L_ERC

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss

Dataset

BBH

Follow for update

@wizwand_team Discord

Related Benchmarks

Comprehensive Chinese Evaluation on C-Eval General Intelligence Evaluation on AGI-Eval Question Answering on TriviaQA (Accuracy)

© 2026 wizwand

Blog Contact Changelog

Privacy Policy Terms of Service FAQs