Galileo Tool Tasks - xLAM Multiple Tool Multiple Call Leaderboard — The Aggregate

Galileo Tool Tasks - xLAM Multiple Tool Multiple Call — leaderboard

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

Top models

#	Model	Score
1	GPT-4o Mini	99
2	Gemini 2.0 Flash (001)	98
3	GPT-4o (2024-11-20)	98
4	Llama 3.3 70B Instruct	97
5	Gemini 1.5 Pro	97
6	Llama 3.1 8B Instruct	96
7	Ministral-8B-Instruct-2410	95
8	Mistral Large 2 (Nov) Instruct (2411)	94
9	Gemini 1.5 Flash	93
10	Mistral Small 3	92
11	Claude 3.5 Sonnet (20241022)	88
12	Claude 3.5 Haiku (20241022)	88
13	Claude 3.7 Sonnet (20250219)	82
14	O3 Mini (2025-01-31)	43
15	O1 (2024-12-17)	43

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