Galileo Tool Tasks - tau Long Context Leaderboard — The Aggregate

Galileo Tool Tasks - tau Long Context — leaderboard

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

Top models

#	Model	Score
1	Claude 3.7 Sonnet (20250219)	100
2	O1 (2024-12-17)	98
3	Qwen 2.5 72B Instruct	92
4	Mistral Small 3	92
5	GPT-4o (2024-11-20)	92
6	Gemini 2.0 Flash (001)	90
7	Gemini 1.5 Flash	89
8	O3 Mini (2025-01-31)	84
9	Mistral Large 2 (Nov) Instruct (2411)	83
10	Gemini 1.5 Pro	75
11	Ministral-8B-Instruct-2410	73
12	Llama 3.3 70B Instruct	72
13	Claude 3.5 Haiku (20241022)	72
14	Claude 3.5 Sonnet (20241022)	68
15	GPT-4o Mini	51

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