cd/entity/BFCL V4· home entities BFCL V4
grep -l @bfcl v4 /news/*.json | wc -l → 1

BFCL V4

mentions 1 type Person feed RSS

// recent coverage 1 mentions

09:24
2026-09-22
codecut.ai
large-language-models

Same prompt, same endpoint, different score

A test of a small prompt edit on 100 single-call tool-calling cases from UC Berkeley's BFCL V4 benchmark found the edit reduced invented optional arguments from 14 to 7 across three runs but produced …

// co-occurs with top 6 entities
// topics top 3 topics