List your company

Commonsense Reasoning on CommonSenseQA (ACC, BS, ECE, CL)

0.1054BSBase Model (Q0)
0.0945160.1679830.241450.314917Jan 27, 2026

Evaluation results

MethodLinks
Base Model (Q0)Model Scale=14B2026.010.105482.560.0173-0.7201
Isotonic RegressionBackbone=Qwen3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1119—0.0219-0.717
Isotonic RegressionModel Scale=14B, Category=Supervised Baseline2026.010.1135—0.019-0.7145
Base Model (Q0)Backbone=Qwen3-8B2026.010.116682.880.0601-0.7122
TS (Supervised)Backbone=Qwen3-8B, Protocol=Supervised Post-hoc2026.010.1166—0.0524-0.7122
Base Model (Q0)Backbone=Qwen3-8B, Method Category=Standard Model2026.010.116682.880.0601-0.7122
Temperature ScalingBackbone=Qwen3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1166—0.0524-0.7122
Temperature ScalingModel Scale=14B, Category=Supervised Baseline2026.010.1193—0.064-0.7087
Histogram BinningBackbone=Qwen3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1249—0.0254-0.7039
Base Model (Q0)Model Scale=4B2026.010.125278.460.0524-0.6594
Isotonic RegressionModel Scale=4B, Category=Supervised Baseline2026.010.1259—0.0286-0.6767
Ours (Label-Free Framework)Model Scale=14B2026.010.126283.370.0232-0.7075
Ours (Label-Free)Backbone=Qwen3-8B, Protocol=Label-Free Post-hoc2026.010.129183.290.0389-0.7038
label-free post-processing frameworkBackbone=Qwen3-8B, Method Category=Label Free2026.010.129183.290.0389-0.7038
Histogram BinningModel Scale=14B, Category=Supervised Baseline2026.010.1295—0.022-0.6985
Temperature ScalingModel Scale=4B, Category=Supervised Baseline2026.010.1322—0.046-0.6704
Instruct Model (Q1)Backbone=Qwen3-8B2026.010.14382.880.1385-0.6859
Instruct Model (Q1)Backbone=Qwen3-8B, Method Category=Standard Model2026.010.14382.880.1385-0.6859
Ours (Label-Free Framework)Model Scale=4B2026.010.143880.670.0297-0.6629
Histogram BinningModel Scale=4B, Category=Supervised Baseline2026.010.1449—0.0283-0.6577
Instruct Model (Q1)Model Scale=14B2026.010.151282.80.1483-0.6768
Isotonic RegressionBackbone=LLaMA-3.1-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1616—0.0427-0.6247
Base Model (Q0)Model Scale=1.7B2026.010.163670.840.0517-0.5449
Histogram BinningBackbone=LLaMA-3.1-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1655—0.0445-0.6207
Ours (Label-Free)Backbone=LLaMA-3.1-8B, Protocol=Label-Free Post-hoc2026.010.165778.710.029-0.6214
label-free post-processing frameworkBackbone=LLaMA-3.1-8B, Method Category=Label Free2026.010.165778.710.029-0.6214
Isotonic RegressionModel Scale=1.7B, Category=Supervised Baseline2026.010.169—0.0443-0.5468
Base Model (Q0)Backbone=LLaMA-3.1-8B2026.010.169870.930.0342-0.5395
Base Model (Q0)Backbone=LLaMA-3.1-8B, Method Category=Standard Model2026.010.169870.930.0342-0.5395
Instruct Model (Q1)Model Scale=4B2026.010.170380.260.166-0.6323
Temperature ScalingModel Scale=1.7B, Category=Supervised Baseline2026.010.1727—0.0645-0.5431
TS (Supervised)Backbone=LLaMA-3.1-8B, Protocol=Supervised Post-hoc2026.010.1749—0.0935-0.6114
Temperature ScalingBackbone=LLaMA-3.1-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1749—0.0935-0.6114
Histogram BinningBackbone=Ministral-3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1771—0.0354-0.5633
Isotonic RegressionBackbone=Ministral-3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1773—0.0345-0.5631
Ours (Label-Free)Backbone=Ministral-3-8B, Protocol=Label-Free Post-hoc2026.010.177774.30.0295-0.5653
label-free post-processing frameworkBackbone=Ministral-3-8B, Method Category=Label Free2026.010.177774.30.0295-0.5653
TS (Supervised)Backbone=Ministral-3-8B, Protocol=Supervised Post-hoc2026.010.1899—0.074-0.5505
Temperature ScalingBackbone=Ministral-3-8B, Method Category=Supervised Baseline, Calibration Protocol=Supervised2026.010.1899—0.074-0.5505
Histogram BinningModel Scale=1.7B, Category=Supervised Baseline2026.010.1934—0.0257-0.5224
Base Model (Q0)Backbone=Ministral-3-8B2026.010.19670.270.1388-0.5067
Base Model (Q0)Backbone=Ministral-3-8B, Method Category=Standard Model2026.010.19670.270.1388-0.5067
Base Model (Q0)Model Scale=0.6B2026.010.196658.560.0211-0.389
Ours (Label-Free Framework)Model Scale=1.7B2026.010.200271.660.0885-0.5165
Instruct Model (Q1)Backbone=LLaMA-3.1-8B2026.010.20378.620.1999-0.5832
Instruct Model (Q1)Backbone=LLaMA-3.1-8B, Method Category=Standard Model2026.010.20378.620.1999-0.5832
Instruct Model (Q1)Backbone=Ministral-3-8B2026.010.204174.040.1682-0.5363
Instruct Model (Q1)Backbone=Ministral-3-8B, Method Category=Standard Model2026.010.204174.040.1682-0.5363
Isotonic RegressionModel Scale=0.6B, Category=Supervised Baseline2026.010.2309—0.0155-0.3359
Temperature ScalingModel Scale=0.6B, Category=Supervised Baseline2026.010.235—0.0315-0.3318
Histogram BinningModel Scale=0.6B, Category=Supervised Baseline2026.010.237—0.0236-0.3297
Instruct Model (Q1)Model Scale=1.7B2026.010.257971.580.2574-0.4579
Ours (Label-Free Framework)Model Scale=0.6B2026.010.284756.670.2182-0.2821
Instruct Model (Q1)Model Scale=0.6B2026.010.377556.670.3767-0.1893