List your company

Uncertainty Estimation on JudgeBench (test)

71.53AUROCEnergy
40.933248.876656.8264.7634Dec 23, 2025

Evaluation results

MethodLinks
EnergyBackbone Model=GPT-OSS OSS 20B2025.1271.53
ProbeBackbone Model=QWEN 32B2025.1271.17
VerbalisedBackbone Model=QWEN 32B2025.1269.2
CoERBackbone Model=GPT-OSS OSS 20B2025.1269.12
ProbeBackbone Model=J1 QWEN 32B2025.1269.05
VerbalisedBackbone Model=J1 QWEN 32B2025.1268.86
CoECBackbone Model=GPT-OSS OSS 20B2025.1268.46
EnergyBackbone Model=QWEN 32B2025.1267.79
Sem. EntropyBackbone Model=J1 QWEN 32B2025.1266.87
Sem. EntropyBackbone Model=QWEN 32B2025.1265.63
VerbalisedBackbone Model=GPT-OSS OSS 20B2025.1264.47
Sem. EntropyBackbone Model=GPT-OSS OSS 20B2025.1264.42
EntropyBackbone Model=J1 QWEN 32B2025.1264.33
MaxProbBackbone Model=J1 QWEN 32B2025.1264.27
PerplexityBackbone Model=J1 QWEN 32B2025.1263.88
TempSclBackbone Model=J1 QWEN 32B2025.1263.74
CoTKBackbone Model=GPT-OSS OSS 20B2025.1263.72
ProbeBackbone Model=J1 LLaMA 70B2025.1263.17
CoTKBackbone Model=J1 QWEN 32B2025.1262.9
VerbalisedBackbone Model=J1 LLaMA 70B2025.1262.04
ProbeBackbone Model=GPT-OSS OSS 20B2025.1262.03
Sem. EntropyBackbone Model=J1 LLaMA 70B2025.1260.63
CoERBackbone Model=J1 QWEN 32B2025.1260.36
CoECBackbone Model=J1 QWEN 32B2025.1260.26
CoTKBackbone Model=J1 LLaMA 70B2025.1259.98
PerplexityBackbone Model=J1 LLaMA 70B2025.1259.62
MaxProbBackbone Model=J1 LLaMA 70B2025.1259.61
EntropyBackbone Model=J1 LLaMA 70B2025.1259.6
TempSclBackbone Model=J1 LLaMA 70B2025.1259.6
CoECBackbone Model=J1 LLaMA 70B2025.1259.13
ProbeBackbone Model=LLaMA 70B2025.1258.14
Sem. EntropyBackbone Model=LLaMA 70B2025.1258.13
VerbalisedBackbone Model=LLaMA 70B2025.1257.95
ProbeBackbone Model=J1 LLaMA 8B2025.1255.36
Sem. EntropyBackbone Model=LLaMA 8B2025.1254.71
Sem. EntropyBackbone Model=J1 LLaMA 8B2025.1254.19
VerbalisedBackbone Model=J1 LLaMA 8B2025.1253.5
EnergyBackbone Model=J1 LLaMA 8B2025.1253.34
ProbeBackbone Model=LLaMA 8B2025.1252.38
CoECBackbone Model=LLaMA 70B2025.1252.24
CoERBackbone Model=LLaMA 8B2025.1252.06
TempSclBackbone Model=LLaMA 70B2025.1251.55
TempSclBackbone Model=QWEN 32B2025.1251.53
MaxProbBackbone Model=LLaMA 70B2025.1251.48
MaxProbBackbone Model=QWEN 32B2025.1251.47
PerplexityBackbone Model=LLaMA 70B2025.1251.31
PerplexityBackbone Model=QWEN 32B2025.1251.2
CoTKBackbone Model=LLaMA 70B2025.1251.11
EntropyBackbone Model=LLaMA 70B2025.1251.08
CoTKBackbone Model=J1 LLaMA 8B2025.1250.87
EntropyBackbone Model=J1 LLaMA 8B2025.1250.85
PerplexityBackbone Model=J1 LLaMA 8B2025.1250.81
EntropyBackbone Model=QWEN 32B2025.1250.79
TempSclBackbone Model=J1 LLaMA 8B2025.1250.72
MaxProbBackbone Model=J1 LLaMA 8B2025.1250.67
CoECBackbone Model=J1 LLaMA 8B2025.1250.56
EnergyBackbone Model=LLaMA 70B2025.1250.07
EnergyBackbone Model=J1 LLaMA 70B2025.1250
CoECBackbone Model=LLaMA 8B2025.1249.99
CoERBackbone Model=J1 LLaMA 8B2025.1249.98
CoERBackbone Model=J1 LLaMA 70B2025.1249.82
EnergyBackbone Model=J1 QWEN 32B2025.1249.34
CoTKBackbone Model=QWEN 32B2025.1248.8
EnergyBackbone Model=LLaMA 8B2025.1247.99
CoERBackbone Model=LLaMA 70B2025.1247.81
VerbalisedBackbone Model=LLaMA 8B2025.1246.83
EntropyBackbone Model=GPT-OSS OSS 20B2025.1246.82
EntropyBackbone Model=LLaMA 8B2025.1246.81
MaxProbBackbone Model=LLaMA 8B2025.1246.77
CoTKBackbone Model=LLaMA 8B2025.1246.69
TempSclBackbone Model=LLaMA 8B2025.1246.54
PerplexityBackbone Model=LLaMA 8B2025.1246.44
CoERBackbone Model=QWEN 32B2025.1246.25
CoECBackbone Model=QWEN 32B2025.1245.99
MaxProbBackbone Model=GPT-OSS OSS 20B2025.1243.54
PerplexityBackbone Model=GPT-OSS OSS 20B2025.1243.15
TempSclBackbone Model=GPT-OSS OSS 20B2025.1242.11