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

Home/Benchmarks

Agent Evaluation on BFCL Parity

86.2Accuracy

GLM-5

Updated 1mo ago

Evaluation Results

Method	Links
GLM-5 2026.06		86.2
OpenThinkerAgent-32B 2026.06		85.9

SOTA Paper

GLM-5

GLM-5: from Vibe Coding to Agentic Engineering

Dataset

BFCL

Follow for update

@wizwand_team Discord

Related Benchmarks

Function Calling on BFCL Parity General AI Assistant Task on GAIA-127 (Accuracy)Financial Agent Task on FinanceAgent-Terminal Coding on Aider Polyglot Medical Agent Task on MedAgentBench (Accuracy)

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs