List your company

Confidence Estimation on Global-MMLU Japanese ja (test)

74AUROCSeq. Likelihood
51.1257.066368.94May 29, 2026

Evaluation results

MethodLinks
Seq. LikelihoodBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0574494857
Verbalized Conf.Backbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0572445761
Cross-lingual ProbeBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0572443131
P(True)Backbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0554242121
Mass-Mean ProbeBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.055259732