bfcl@1.0
Assistants
Berkeley Function-Calling Leaderboard: 3,641 function calling tasks for evaluating LLM tool use capabilities across simple, multiple, parallel, and irrelevance categories.
Run this task
CLI:
inspect eval inspect_harbor/bfcl_1_0 --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import bfcl_1_0
eval(bfcl_1_0(), model="openai/gpt-5")Dataset information
| Harbor registry | bfcl@1.0 |
| Inspect task | bfcl_1_0 |
| Version | 1.0 |
| Samples | 3641 |
| Source | https://github.com/ShishirPatil/gorilla |
See Task Parameters for the parameter set shared across all Harbor tasks.