List your company

Confidence Estimation on GUESS

0.1858AccuracyVANILLA-VERB
0.1269360.1422180.15750.172782Jan 5, 2026

Evaluation results

MethodLinks
VANILLA-VERBBackbone=Llama3.1-70b2026.010.18580.655216.92
COT-VERBBackbone=Llama3.1-70b2026.010.18580.701618.24
SCBackbone=Llama3.1-70b2026.010.18580.56882.59
P(TRUE)Backbone=Llama3.1-70b2026.010.18580.79973.29
P(SUFFICIENT)Backbone=Llama3.1-70b2026.010.18580.052781.51
VANILLA-VERBBackbone=Qwen2.5-72b2026.010.16120.670452.81
COT-VERBBackbone=Qwen2.5-72b2026.010.16120.646379
SCBackbone=Qwen2.5-72b2026.010.16120.689312.52
P(TRUE)Backbone=Qwen2.5-72b2026.010.16120.575654.87
P(SUFFICIENT)Backbone=Qwen2.5-72b2026.010.16120.283283.76
VANILLA-VERBBackbone=Llama3.1-8b2026.010.14520.7489-6.58
COT-VERBBackbone=Llama3.1-8b2026.010.14520.702837.84
SCBackbone=Llama3.1-8b2026.010.14520.38149.43
P(TRUE)Backbone=Llama3.1-8b2026.010.14520.670819.91
P(SUFFICIENT)Backbone=Llama3.1-8b2026.010.14520.351768.51
VANILLA-VERBBackbone=Qwen2.5-7b2026.010.12920.486826.99
COT-VERBBackbone=Qwen2.5-7b2026.010.12920.718456.01
SCBackbone=Qwen2.5-7b2026.010.12920.505336.1
P(TRUE)Backbone=Qwen2.5-7b2026.010.12920.378622.04
P(SUFFICIENT)Backbone=Qwen2.5-7b2026.010.12920.266351.44