List your company
ResearchFormerly WizWand

Tool Usage on BFCL Multi-Parallel v2

87.5AccuracyTHINKBRAKE
13.86832.98452.171.216Oct 1, 2025
Updated 6mo ago

Evaluation results

MethodLinks
THINKBRAKEBase Model=Qwen3-4B-Thinking, Stopping Strategy=THINKBRAKE2025.1087.5-18.9
Qwen3-4B-ThinkingBase Model=Qwen3-4B-Thinking, Stopping Strategy=Base2025.1079.2—
NoWaitBase Model=Qwen3-4B-Thinking, Stopping Strategy=NoWait2025.1075-66.5
NoWaitBase Model=Qwen3-4B, Stopping Strategy=NoWait2025.1075-11.1
THINKBRAKEBase Model=Qwen3-4B, Stopping Strategy=THINKBRAKE2025.1075-10.2
Qwen3-4BBase Model=Qwen3-4B, Stopping Strategy=Base2025.1070.8—
Qwen3-14BBase Model=Qwen3-14B, Stopping Strategy=Base2025.1070.8—
Qwen3-32BBase Model=Qwen3-32B, Stopping Strategy=Base2025.1070.8—
THINKBRAKEBase Model=Phi-4-Reasoning, Stopping Strategy=THINKBRAKE2025.1070.8-4.9
NoWaitBase Model=Qwen3-14B, Stopping Strategy=NoWait2025.1062.5-10.9
THINKBRAKEBase Model=Qwen3-14B, Stopping Strategy=THINKBRAKE2025.1062.5-7.6
NoWaitBase Model=Qwen3-32B, Stopping Strategy=NoWait2025.1062.5-14.3
Phi-4-ReasoningBase Model=Phi-4-Reasoning, Stopping Strategy=Base2025.1058.3—
NoWaitBase Model=Phi-4-Reasoning, Stopping Strategy=NoWait2025.1058.3-11.9
THINKBRAKEBase Model=Qwen3-32B, Stopping Strategy=THINKBRAKE2025.1058-13.3
ThinkLessBase Model=Qwen3-4B-Thinking, Stopping Strategy=ThinkLess2025.1045.8-100
THINKBRAKE-pBase Model=Qwen3-4B-Thinking, Stopping Strategy=THINKBRAKE-p2025.1029.2-43.8
DeepSeek-R1-7BBase Model=DeepSeek-R1-7B, Stopping Strategy=Base2025.1029.2—
NoWaitBase Model=DeepSeek-R1-7B, Stopping Strategy=NoWait2025.1020.811
THINKBRAKEBase Model=DeepSeek-R1-7B, Stopping Strategy=THINKBRAKE2025.1016.7-6