Galileo Tool Tasks - BFCL v3 Multi-Turn Missing Parameter: leaderboard

Tool-use evaluation from Galileo covering BFCL v3 cases where required function parameters are missing and must be requested or handled correctly.

Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 19 models tracked.

Top models

#ModelScoreOverall rank
1Claude 3.7 Sonnet (20250219)97#201
2O3 Mini (2025-01-31)93#240
3Gemini 2.0 Flash (001)92#360
4Gemini 1.5 Flash91#618
5O1 (2024-12-17)91#149
6Gemini 1.5 Pro90#445
7GPT-4o (2024-11-20)88#381
8Qwen 2.5 72B Instruct86#454
9Claude 3.5 Sonnet (20241022)85#291
10GPT-4o Mini83#599
11Claude 3.5 Haiku (20241022)79#588
12Mistral Small 376#627
13Mistral Large 2 (Nov) Instruct (2411)75#465
14Llama 3.1 8B Instruct66#1035
15Ministral-8B-Instruct-241066#1094

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=galileo-tool-tasks-bfcl-v3-multi-turn-missing-parameter · How It Works · Data refreshed daily, snapshot 2026-10-20.