List your company

Function Calling on ACEBench

78Atom ScoreR2IF
41.91251.28160.6570.019Apr 22, 2026

Evaluation results

MethodLinks
R2IFModel=Qwen2.5-7B-Instruct2026.047857.59677.17
Binary RewardModel=Qwen2.5-7B-Instruct2026.0476.7499673.9
ToolRLModel=Qwen2.5-7B-Instruct2026.0476.356.59676.27
R2IFModel=Llama3.2-3B-Instruct2026.0473.7519472.9
Binary RewardModel=Llama3.2-3B-Instruct2026.047247.59069.83
SFTModel=Qwen2.5-7B-Instruct2026.0471.354.59473.27
R2IFModel=Qwen2.5-3B-Instruct2026.0470.7269062.23
SFTModel=Llama3.2-3B-Instruct2026.0467.334.55451.93
ToolRLModel=Llama3.2-3B-Instruct2026.0465.7398864.23
R2IFModel=Qwen2.5-1.5B-Instruct2026.0464.720.58857.73
SFTModel=Qwen2.5-3B-Instruct2026.0463.729.54445.73
SFTModel=Qwen2.5-1.5B-Instruct2026.0461.3231633.43
ToolRLModel=Qwen2.5-3B-Instruct2026.045831.59661.83
RawModel=Qwen2.5-7B-Instruct2026.0457.3408861.77
ToolRLModel=Qwen2.5-1.5B-Instruct2026.0452.3268855.43
RawModel=Qwen2.5-3B-Instruct2026.0452259055.67
Binary RewardModel=Qwen2.5-3B-Instruct2026.044920.56043.17
RawModel=Llama3.2-3B-Instruct2026.0445.3171425.43
RawModel=Qwen2.5-1.5B-Instruct2026.0443.713.53029.07
Binary RewardModel=Qwen2.5-1.5B-Instruct2026.0443.314.57845.27