List your company

Confidence Estimation on Global-MMLU Spanish es (test)

74AUROCCross-lingual Probe
39.6848.5957.566.41May 29, 2026

Evaluation results

MethodLinks
Cross-lingual ProbeBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0574520.230.21
Verbalized Conf.Backbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0573550.520.54
Seq. LikelihoodBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0570510.530.59
Mass-Mean ProbeBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0559500.410.12
P(True)Backbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.0541230.260.26