List your company

Correctness Prediction on GPQA

79.42AccuracyLOCUS
74.230475.577776.92578.2723Jan 28, 2026

Evaluation results

MethodLinks
LOCUSTrain samples=10242026.0179.42
LOCUSTrain samples=5122026.0179.18
LOCUSTrain samples=2562026.0179.17
EMBEDLLMTrain samples=2562026.0179.03
EMBEDLLMTrain samples=10242026.0179.02
IRT-NETTrain samples=10242026.0179.02
kNNTrain samples=10242026.0178.93
IRT-NETTrain samples=2562026.0178.87
KMEANSTrain samples=2562026.0178.76
EMBEDLLMTrain samples=5122026.0178.73
EMBEDLLM+Train samples=2562026.0178.69
KMEANSTrain samples=10242026.0178.67
IRT-NETTrain samples=5122026.0178.59
EMBEDLLM+Train samples=10242026.0178.47
kNNTrain samples=5122026.0178.21
EMBEDLLM+Train samples=5122026.0178.08
KMEANSTrain samples=5122026.0176.37
kNNTrain samples=2562026.0174.43