List your company

Ranking Uncertainty Quantification on Steam

0.3133Tau@5EviRank
0.112580.164690.21680.26891Jun 3, 2026

Evaluation results

MethodLinks
EviRankBackbone=Qwen2.52026.060.31330.70950.28750.6587
Verb. 1S top-1Backbone=Llama32026.060.30410.69220.28110.6591
EviRankBackbone=Llama32026.060.30350.68470.2810.6573
Semantic Unc.Backbone=Llama32026.060.27670.68030.23840.6331
Label Prob.Backbone=Llama32026.060.23120.65170.20450.619
Label Prob.Backbone=Qwen2.52026.060.21410.63350.19570.6092
Verb. 1S top-1Backbone=Qwen2.52026.060.21310.63240.19530.6078
Semantic Unc.Backbone=Qwen2.52026.060.21250.63110.19490.607
EviRankBackbone=Mistral2026.060.18050.61630.16620.5931
Verb. 1S top-1Backbone=Mistral2026.060.14170.58640.12050.5631
Semantic Unc.Backbone=Mistral2026.060.1390.58420.11960.5622
Label Prob.Backbone=Mistral2026.060.12030.57330.10350.5541