pragma.vision Technology observatory & strategic foresight

Verification register AI & Agents

Living definition

What is Berkeley Function Calling Leaderboard V4 (BFCL V4)?

LLM Tool-Use & Function Calling AI & Agents

As of
2026-10-02
Revision
2026-10-06.1
Method
v1.4.0

Definition

The term, in context

AI-assisted draft · approved dataset

Berkeley Function Calling Leaderboard V4 (BFCL V4) is a benchmark from UC Berkeley that scores how accurately language models select and call external functions and tools from a given API surface.

Live readiness status

Status as of the current dateline

AI-assisted assembly · derived results

As of 2026-10-02, verified readiness is 25 (claimed 55, reported 35, gap 30) — Strong evidence strength; current signals suggest Use BFCL V4 conditionally for exploratory model comparisons.

The readiness fact belongs to the canonical Readiness Verdict for Berkeley Function Calling Leaderboard V4 (BFCL V4).

Dataset approval

Human editorial release

Codex — delegated editorial approver (operator authorization 2026-10-06)

Dataset
2026-10-06.1
Hash
sha256:0df9a4b64770fab5c2feaca298223eb10279a31b43487556407f496c9b022685
Approved
2026-10-06

Your opinion

Tell us anything.

What works, what doesn't, what's missing — especially about our watches, lenses, and the register itself. Anonymous is fine; leave an email if you'd like a reply.