Galileo Tool Tasks - BFCL v3 Irrelevance Leaderboard — The Aggregate

Galileo Tool Tasks - BFCL v3 Irrelevance — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 19 models tracked.

Top models

#	Model	Score
1	Qwen 2.5 72B Instruct	99
2	Gemini 1.5 Flash	98
3	Gemini 2.0 Flash (001)	98
4	GPT-4o (2024-11-20)	98
5	O1 (2024-12-17)	98
6	Claude 3.7 Sonnet (20250219)	97
7	O3 Mini (2025-01-31)	97
8	GPT-4o Mini	94
9	Gemini 1.5 Pro	94
10	Llama 3.3 70B Instruct	90
11	Claude 3.5 Sonnet (20241022)	90
12	Mistral Large 2 (Nov) Instruct (2411)	87
13	Claude 3.5 Haiku (20241022)	84
14	Mistral Small 3	82
15	Llama 3.1 8B Instruct	48

Interactive version: theaggregate.ai/benchmark?slug=galileo-tool-tasks-bfcl-v3-irrelevance · How the rankings work · Data refreshed daily, snapshot 2026-07-22.