Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

Galileo Tool Tasks - Multi Turn — leaderboard

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

Top models

#ModelScore
1Claude 3.7 Sonnet (20250219)95
2Gemini 2.0 Flash (001)93
3O1 (2024-12-17)92
4Gemini 1.5 Pro91
5Gemini 1.5 Flash91
6O3 Mini (2025-01-31)90
7GPT-4o (2024-11-20)88
8Qwen 2.5 72B Instruct84
9GPT-4o Mini82
10Mistral Small 378
11Claude 3.5 Sonnet (20241022)77
12Claude 3.5 Haiku (20241022)75
13Mistral Large 2 (Nov) Instruct (2411)75
14Llama 3.3 70B Instruct69
15Ministral-8B-Instruct-241065

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

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.