List your company
ResearchFormerly WizWand

Tool Usage on BFCL Parallel v1

95.5AccuracyTHINKBRAKE
39.8654.30568.7583.195Oct 1, 2025
Updated 6mo ago

Evaluation results

MethodLinks
THINKBRAKEBase Model=Qwen3-4B-Thinking, Stopping Strategy=THINKBRAKE2025.1095.5-26.8
Qwen3-4B-ThinkingBase Model=Qwen3-4B-Thinking, Stopping Strategy=Base2025.1093.5—
THINKBRAKEBase Model=Qwen3-14B, Stopping Strategy=THINKBRAKE2025.1093-21.2
Qwen3-32BBase Model=Qwen3-32B, Stopping Strategy=Base2025.1093—
Qwen3-14BBase Model=Qwen3-14B, Stopping Strategy=Base2025.1092—
NoWaitBase Model=Qwen3-32B, Stopping Strategy=NoWait2025.1091-13
THINKBRAKEBase Model=Qwen3-32B, Stopping Strategy=THINKBRAKE2025.1091-14.3
Qwen3-4BBase Model=Qwen3-4B, Stopping Strategy=Base2025.1090—
NoWaitBase Model=Qwen3-14B, Stopping Strategy=NoWait2025.1090-16.3
THINKBRAKEBase Model=Qwen3-4B, Stopping Strategy=THINKBRAKE2025.1089.5-16.5
NoWaitBase Model=Qwen3-4B-Thinking, Stopping Strategy=NoWait2025.1088.5-44.4
NoWaitBase Model=Qwen3-4B, Stopping Strategy=NoWait2025.1088-13.5
Phi-4-ReasoningBase Model=Phi-4-Reasoning, Stopping Strategy=Base2025.1087.5—
THINKBRAKEBase Model=Phi-4-Reasoning, Stopping Strategy=THINKBRAKE2025.1084.52.7
NoWaitBase Model=Phi-4-Reasoning, Stopping Strategy=NoWait2025.1081-1.3
ThinkLessBase Model=Qwen3-4B-Thinking, Stopping Strategy=ThinkLess2025.1079.5-100
THINKBRAKE-pBase Model=Qwen3-4B-Thinking, Stopping Strategy=THINKBRAKE-p2025.1078-26.9
NoWaitBase Model=DeepSeek-R1-7B, Stopping Strategy=NoWait2025.1062-4
DeepSeek-R1-7BBase Model=DeepSeek-R1-7B, Stopping Strategy=Base2025.1052.5—
THINKBRAKEBase Model=DeepSeek-R1-7B, Stopping Strategy=THINKBRAKE2025.1042-14.6