List your company

Knowledge Evaluation on MMLU-Redux

0.1083Brier ScoreIsotonic Regression
0.1028320.1397410.176650.213559Jan 27, 2026

Evaluation results

MethodLinks
Isotonic RegressionBackbone=Qwen3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1083—0.0186-0.7245
Temperature ScalingBackbone=Qwen3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1116—0.0584-0.7212
Histogram BinningBackbone=Qwen3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1198—0.0177-0.713
Base Model (Q0)Backbone=Qwen3-8B, Method Category=Standard Model2026.010.122977.350.0326-0.6506
label-free post-processing frameworkBackbone=Qwen3-8B, Method Category=Label Free2026.010.123283.280.0659-0.7096
Base Model (Q0)Backbone=Ministral-3-8B, Method Category=Standard Model2026.010.127875.630.0534-0.6285
Instruct Model (Q1)Backbone=Qwen3-8B, Method Category=Standard Model2026.010.133783.280.125-0.6991
Histogram BinningBackbone=Ministral-3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1494—0.0528-0.6427
Isotonic RegressionBackbone=Ministral-3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1509—0.0465-0.6412
label-free post-processing frameworkBackbone=Ministral-3-8B, Method Category=Label Free2026.010.151980.520.0664-0.6534
Temperature ScalingBackbone=Ministral-3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1571—0.0546-0.635
Base Model (Q0)Backbone=LLaMA-3.1-8B, Method Category=Standard Model2026.010.15865.420.0176-0.4962
Instruct Model (Q1)Backbone=Ministral-3-8B, Method Category=Standard Model2026.010.17279.210.1628-0.6201
Isotonic RegressionBackbone=LLaMA-3.1-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1807—0.0185-0.5366
Temperature ScalingBackbone=LLaMA-3.1-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1874—0.0352-0.5299
Histogram BinningBackbone=LLaMA-3.1-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1889—0.0188-0.5285
label-free post-processing frameworkBackbone=LLaMA-3.1-8B, Method Category=Label Free2026.010.215371.740.1679-0.5022
Instruct Model (Q1)Backbone=LLaMA-3.1-8B, Method Category=Standard Model2026.010.24571.740.2417-0.4724