List your company

Calibration on NQ

0.046ECETemp. Scaling
0.0207120.1914060.36210.532794Jan 6, 2026Jan 12, 2026Jan 18, 2026Jan 25, 2026Jan 31, 2026Feb 6, 2026Feb 13, 2026

Evaluation results

MethodLinks
Temp. ScalingModel=Llama3.1-8B-Instruct, Unsupervised=false2026.010.046—0.1743
Temp. ScalingModel=Olmo2-7B-Instruct, Unsupervised=false2026.010.0742—0.1826
Temp. ScalingModel=Qwen2.5-7B-Instruct, Unsupervised=false2026.010.1304—0.1938
VerbalizationModel=Olmo2-7B-Instruct, Unsupervised=true2026.010.203—0.2478
BaseCal-ReEvalModel=Olmo2-7B-Instruct, Unsupervised=true2026.010.2304—0.2312
CDKCBackbone=Qwen2.5-7B-Instruct, Optimization Rounds=22026.020.2401——
BaseCal-ReEvalModel=Llama3.1-8B-Instruct, Unsupervised=true2026.010.2462—0.2349
BaseCal-ProjModel=Llama3.1-8B-Instruct, Unsupervised=true2026.010.2488—0.2358
VerbalizationModel=Llama3.1-8B-Instruct, Unsupervised=true2026.010.2689—0.2507
BaseCal-ProjModel=Olmo2-7B-Instruct, Unsupervised=true2026.010.2712—0.2511
NAACLBackbone=Llama-3.1-8B-Instruct2026.010.3010.724—
P(true)Model=Olmo2-7B-Instruct, Unsupervised=true2026.010.312—0.3166
CDKCBackbone=Qwen2.5-7B-Instruct2026.020.3132——
BaseCal-ReEvalModel=Qwen2.5-7B-Instruct, Unsupervised=true2026.010.3161—0.2714
NAACLBackbone=Qwen2.5-7B-Instruct2026.010.3220.754—
GRPOBackbone=Qwen2.5-7B-Instruct2026.020.3283——
BaseCal-ProjModel=Qwen2.5-7B-Instruct, Unsupervised=true2026.010.3382—0.288
Noise-awareBackbone=Llama-3.1-8B-Instruct2026.010.3510.618—
NAACLBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.360.656—
P(true)Model=Qwen2.5-7B-Instruct, Unsupervised=true2026.010.3723—0.3708
Noise-awareBackbone=Qwen2.5-7B-Instruct2026.010.380.649—
NAACLBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.4090.726—
CoTBackbone=Qwen2.5-7B-Instruct2026.010.4140.703—
Semantic EntropyModel=Olmo2-7B-Instruct, Unsupervised=true2026.010.4178—0.3646
CoTBackbone=Llama-3.1-8B-Instruct2026.010.4230.611—
Label-only SFTBackbone=Qwen2.5-7B-Instruct2026.010.4250.691—
Noise-awareBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.4250.584—
EnsembleBackbone=Llama-3.1-8B-Instruct2026.010.4280.619—
VanillaBackbone=Qwen2.5-7B-Instruct2026.010.4380.71—
VanillaModel=Olmo2-7B-Instruct, Unsupervised=true2026.010.4404—0.3739
Label-only SFTBackbone=Llama-3.1-8B-Instruct2026.010.4410.658—
P(true)Model=Llama3.1-8B-Instruct, Unsupervised=true2026.010.4439—0.3972
EnsembleBackbone=Qwen2.5-7B-Instruct2026.010.4510.693—
VanillaModel=Llama3.1-8B-Instruct, Unsupervised=true2026.010.4532—0.3882
VanillaBackbone=Llama-3.1-8B-Instruct2026.010.4650.577—
VerbalizationModel=Qwen2.5-7B-Instruct, Unsupervised=true2026.010.4718—0.4623
Semantic EntropyModel=Llama3.1-8B-Instruct, Unsupervised=true2026.010.4927—0.4371
Label-only SFTBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.4930.588—
VanillaBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.5040.637—
Noise-awareBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.5050.535—
Semantic EntropyModel=Qwen2.5-7B-Instruct, Unsupervised=true2026.010.5192—0.4502
VanillaBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.5220.668—
EnsembleBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.5250.592—
CoTBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.5310.639—
VanillaModel=Qwen2.5-7B-Instruct, Unsupervised=true2026.010.5562—0.4839
EnsembleBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.5610.616—
BARRELBackbone=Qwen2.5-7B-Instruct2026.020.561——
CoTBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.5780.641—
Know WhatBackbone=Qwen2.5-7B-Instruct2026.020.6171——
Label-only SFTBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.6290.585—
Vanilla SFTBackbone=Qwen2.5-7B-Instruct2026.020.6315——
LLKD-SFTBackbone=Qwen2.5-7B-Instruct2026.020.6408——
Vanilla LLMBackbone=Qwen2.5-7B-Instruct2026.020.6411——
CGKEBackbone=Qwen2.5-7B-Instruct2026.020.6423——
CRew-DPOBackbone=Qwen2.5-7B-Instruct2026.020.6782——
Clustered Self-AssessmentBackbone=Qwen2.5-7B2026.06——0.1706
Clustered Self-AssessmentBackbone=Qwen2.5-14B2026.06——0.1729
Clustered Self-AssessmentBackbone=Qwen2.5-32B2026.06——0.1597
Clustered Self-AssessmentBackbone=Qwen3-14B2026.06——0.1611
Clustered Self-AssessmentBackbone=Qwen3-30B-A3B2026.06——0.1656
Clustered Self-AssessmentBackbone=Gemma-3-12B2026.06——0.1809
Clustered Self-AssessmentBackbone=Gemma-3-27B2026.06——0.1736
NSEBackbone=Qwen2.5-7B2026.06——0.2007
NSEBackbone=Qwen2.5-14B2026.06——0.2205
NSEBackbone=Qwen2.5-32B2026.06——0.1993
NSEBackbone=Qwen3-14B2026.06——0.193
NSEBackbone=Qwen3-30B-A3B2026.06——0.2011
NSEBackbone=Gemma-3-12B2026.06——0.2581
NSEBackbone=Gemma-3-27B2026.06——0.2462
P(True)Backbone=Qwen2.5-7B2026.06——0.1993
P(True)Backbone=Qwen2.5-14B2026.06——0.2128
P(True)Backbone=Qwen2.5-32B2026.06——0.1918
P(True)Backbone=Qwen3-14B2026.06——0.2015
P(True)Backbone=Qwen3-30B-A3B2026.06——0.2191
P(True)Backbone=Gemma-3-12B2026.06——0.2462
P(True)Backbone=Gemma-3-27B2026.06——0.2354
ProbabilityBackbone=Qwen2.5-7B2026.06——0.2471
ProbabilityBackbone=Qwen2.5-14B2026.06——0.3409
ProbabilityBackbone=Qwen2.5-32B2026.06——0.3155
ProbabilityBackbone=Qwen3-14B2026.06——0.3149
ProbabilityBackbone=Qwen3-30B-A3B2026.06——0.3208
ProbabilityBackbone=Gemma-3-12B2026.06——0.3207
ProbabilityBackbone=Gemma-3-27B2026.06——0.3503