List your company

Task Completion Rate on ToolBench

37.8Task Completion Rate (TCR)DPO – ADARUBRIC-DA
17.62422.86228.133.338Mar 22, 2026

Evaluation results

MethodLinks
DPO – ADARUBRIC-DABackbone=Qwen2.5-7B, Evaluation Protocol=DPO training2026.0337.8
DPO – ADARUBRIC-GMBackbone=Qwen2.5-7B, Evaluation Protocol=DPO training2026.0335.6
DPO – ADARUBRIC-WMBackbone=Qwen2.5-7B, Evaluation Protocol=DPO training2026.0334.2
DPO – PrometheusBackbone=Qwen2.5-7B, Evaluation Protocol=DPO training2026.0329.3
DPO – G-EvalBackbone=Qwen2.5-7B, Evaluation Protocol=DPO training2026.0327.6
DPO – Random pairsBackbone=Qwen2.5-7B, Evaluation Protocol=DPO training2026.0324.8
SFT – Success onlyBackbone=Qwen2.5-7B2026.0323.1
BaseBackbone=Qwen2.5-7B, Evaluation Protocol=zero-shot2026.0318.4