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

Home/Benchmarks

Language Model Evaluation on MMLU-Pro

77.54AS

AgentSociety

Updated 7d ago

Evaluation Results

Method	Links
AgentSociety 2026.05		77.54	75.68	1.86	78.21

SOTA Paper

AgentSociety

AgentSociety: Incentivizing Agentic Social Intelligence

Dataset

MMLU

Follow for update

@wizwand_team Discord

Related Benchmarks

Language Model Evaluation on Open LeaderBoard v2 Multi-task Routing on Multi-task Request Simulation Software Engineering Task Solving on SWE-bench

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs