List your company

Clarification Seeking on ALFWorld Clarification (test)

68.9Success RateUncertainty Decomposition
18.66831.70944.7557.791Jun 17, 2026

Evaluation results

MethodLinks
Uncertainty DecompositionModel=GLM-4.72026.0668.973.760.966.768.9
ReAct+UEModel=GLM-4.72026.0664.798.54.58.758.8
UAMModel=DeepSeek-v3.2-exp2026.065684.87076.779.8
UAMModel=GLM-4.72026.0654.781.82538.361.3
ReAct+UEModel=DeepSeek-v3.2-exp2026.065467.59077.174.6
UAMModel=GPT-5.12026.0647.173.742.453.864.7
Uncertainty DecompositionModel=GPT-5.12026.0645.793.848.463.875.7
ReAct+UEModel=GPT-5.12026.0636.264.325.736.755.1
Uncertainty DecompositionModel=GPT-OSS-120B2026.0628.471.472.972.271.6
ReAct+UEModel=GPT-OSS-120B2026.0627.155.620.429.951
UAMModel=GPT-OSS-120B2026.0626.15015.924.152.2
ReAct+UEModel=Qwen3.5-35B2026.0623.976.530.243.352.1
Uncertainty DecompositionModel=DeepSeek-v3.2-exp2026.0622.959.192.972.263.9
UAMModel=Qwen3.5-35B2026.0621.465.75056.858.3
Uncertainty DecompositionModel=Qwen3.5-35B2026.0620.656.174.263.961.8