List your company

Confidence Estimation on Global-MMLU Russian (test)

75AUROCSeq. Likelihood
43.851.96068.1May 29, 2026

Evaluation results

MethodLinks
Seq. LikelihoodBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0575475462
Verbalized Conf.Backbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0573495150
Cross-lingual ProbeBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0572433942
Mass-Mean ProbeBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.056257514
P(True)Backbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0545212121