List your company

Clarification Seeking on WebShop Clarification (test)

0.245Success RateReAct+UE
0.0110.071750.13250.19325Jun 17, 2026

Evaluation results

MethodLinks
ReAct+UEModel=GPT-5.12026.060.2450.2350.0850.1250.404
Uncertainty DecompositionModel=GLM-4.72026.060.190.6940.8290.7560.722
UAMModel=GPT-5.12026.060.1890.2380.1020.1430.368
Uncertainty DecompositionModel=GPT-5.12026.060.1360.2670.1050.1510.444
UAMModel=GLM-4.72026.060.1140.5240.2680.3550.494
ReAct+UEModel=GLM-4.72026.060.1120.6250.30.4050.551
Uncertainty DecompositionModel=DeepSeek-v3.2-exp2026.060.080.5470.70.6140.56
ReAct+UEModel=DeepSeek-v3.2-exp2026.060.070.1390.10.1160.24
Uncertainty DecompositionModel=Qwen3.5-35B2026.060.0640.50.5110.5050.5
ReAct+UEModel=Qwen3.5-35B2026.060.0510.0970.060.0740.242
Uncertainty DecompositionModel=GPT-OSS-120B2026.060.0440.2450.2550.250.209
UAMModel=DeepSeek-v3.2-exp2026.060.040.1730.180.1760.16
UAMModel=GPT-OSS-120B2026.060.0330.2170.2220.220.211
ReAct+UEModel=GPT-OSS-120B2026.060.0230.1840.1490.1650.174
UAMModel=Qwen3.5-35B2026.060.020.1780.160.1680.21