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 - BFCL v3 Multi-Turn Base Single Function — leaderboard

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

Top models

#ModelScore
1Claude 3.7 Sonnet (20250219)96
2O1 (2024-12-17)96
3Gemini 2.0 Flash (001)93
4Gemini 1.5 Pro92
5Gemini 1.5 Flash89
6GPT-4o (2024-11-20)89
7O3 Mini (2025-01-31)84
8GPT-4o Mini83
9Ministral-8B-Instruct-241081
10Mistral Large 2 (Nov) Instruct (2411)78
11Qwen 2.5 72B Instruct77
12Mistral Small 377
13Llama 3.1 8B Instruct76
14Claude 3.5 Sonnet (20241022)75
15Llama 3.3 70B Instruct73

Interactive version: theaggregate.ai/benchmark?slug=galileo-tool-tasks-bfcl-v3-multi-turn-base-single-function · 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.