List your company

Multi-task Question Answering on ARC, OBQA, and Riddle Combined (test)

62.69AccuracyREALM
23.409233.607143.80554.0029Apr 19, 2026

Evaluation results

MethodLinks
REALMModel Size=Large (64.76%), Distribution=Dist. 2, Noise Type=Systematic2026.0462.69
REALMModel Size=Large (64.76%), Distribution=Dist. 2, Noise Type=Asymmetric2026.0462.67
REALMModel Size=Large (64.76%), Distribution=Dist. 2, Noise Type=Uniform2026.0462.41
REALMModel Size=Large (64.76%), Distribution=Dist. 3, Noise Type=Uniform2026.0462.32
REALMModel Size=Large (64.76%), Distribution=Dist. 3, Noise Type=Asymmetric2026.0461.66
NOISYModel Size=Large (64.76%), Distribution=Dist. 2, Noise Type=Uniform2026.0461.49
REALMModel Size=Large (64.76%), Distribution=Dist. 1, Noise Type=Uniform2026.0461.38
REALMModel Size=Large (64.76%), Distribution=Dist. 3, Noise Type=Systematic2026.0461.08
NOISYModel Size=Large (64.76%), Distribution=Dist. 2, Noise Type=Systematic2026.0460.92
REALMModel Size=Large (64.76%), Distribution=Dist. 1, Noise Type=Asymmetric2026.0460.44
NOISYModel Size=Large (64.76%), Distribution=Dist. 2, Noise Type=Asymmetric2026.0460.44
REALMModel Size=Large (64.76%), Distribution=Dist. 1, Noise Type=Systematic2026.0460.14
NOISYModel Size=Large (64.76%), Distribution=Dist. 3, Noise Type=Uniform2026.0459.1
NOISYModel Size=Large (64.76%), Distribution=Dist. 3, Noise Type=Systematic2026.0458.46
NOISYModel Size=Large (64.76%), Distribution=Dist. 3, Noise Type=Asymmetric2026.0457.77
NOISYModel Size=Large (64.76%), Distribution=Dist. 1, Noise Type=Uniform2026.0454.9
NOISYModel Size=Large (64.76%), Distribution=Dist. 1, Noise Type=Systematic2026.0453.91
NOISYModel Size=Large (64.76%), Distribution=Dist. 1, Noise Type=Asymmetric2026.0448.69
REALMModel Size=Base (46.05%), Distribution=Dist. 2, Noise Type=Asymmetric2026.0444.18
REALMModel Size=Base (46.05%), Distribution=Dist. 2, Noise Type=Uniform2026.0444.07
REALMModel Size=Base (46.05%), Distribution=Dist. 2, Noise Type=Systematic2026.0443.59
REALMModel Size=Base (46.05%), Distribution=Dist. 3, Noise Type=Systematic2026.0442.83
NOISYModel Size=Base (46.05%), Distribution=Dist. 2, Noise Type=Systematic2026.0442.67
NOISYModel Size=Base (46.05%), Distribution=Dist. 2, Noise Type=Uniform2026.0442.64
REALMModel Size=Base (46.05%), Distribution=Dist. 3, Noise Type=Asymmetric2026.0442.62
REALMModel Size=Base (46.05%), Distribution=Dist. 3, Noise Type=Uniform2026.0442.51
NOISYModel Size=Base (46.05%), Distribution=Dist. 2, Noise Type=Asymmetric2026.0442.48
REALMModel Size=Base (46.05%), Distribution=Dist. 1, Noise Type=Uniform2026.0442.41
REALMModel Size=Base (46.05%), Distribution=Dist. 1, Noise Type=Systematic2026.0442.05
REALMModel Size=Base (46.05%), Distribution=Dist. 1, Noise Type=Asymmetric2026.0441.93
NOISYModel Size=Base (46.05%), Distribution=Dist. 3, Noise Type=Asymmetric2026.0441.08
NOISYModel Size=Base (46.05%), Distribution=Dist. 3, Noise Type=Systematic2026.0440.94
NOISYModel Size=Base (46.05%), Distribution=Dist. 3, Noise Type=Uniform2026.0440.3
NOISYModel Size=Base (46.05%), Distribution=Dist. 1, Noise Type=Uniform2026.0438.44
NOISYModel Size=Base (46.05%), Distribution=Dist. 1, Noise Type=Asymmetric2026.0438.25
NOISYModel Size=Base (46.05%), Distribution=Dist. 1, Noise Type=Systematic2026.0437.75
REALMModel Size=Small (28.57%), Distribution=Dist. 2, Noise Type=Asymmetric2026.0428.71
NOISYModel Size=Small (28.57%), Distribution=Dist. 2, Noise Type=Asymmetric2026.0428.62
REALMModel Size=Small (28.57%), Distribution=Dist. 2, Noise Type=Uniform2026.0428.57
NOISYModel Size=Small (28.57%), Distribution=Dist. 2, Noise Type=Uniform2026.0428.39
REALMModel Size=Small (28.57%), Distribution=Dist. 2, Noise Type=Systematic2026.0428.39
REALMModel Size=Small (28.57%), Distribution=Dist. 3, Noise Type=Uniform2026.0428.16
REALMModel Size=Small (28.57%), Distribution=Dist. 3, Noise Type=Systematic2026.0428.16
REALMModel Size=Small (28.57%), Distribution=Dist. 3, Noise Type=Asymmetric2026.0427.98
REALMModel Size=Small (28.57%), Distribution=Dist. 1, Noise Type=Systematic2026.0427.95
NOISYModel Size=Small (28.57%), Distribution=Dist. 2, Noise Type=Systematic2026.0427.93
REALMModel Size=Small (28.57%), Distribution=Dist. 1, Noise Type=Uniform2026.0427.89
REALMModel Size=Small (28.57%), Distribution=Dist. 1, Noise Type=Asymmetric2026.0427.49
NOISYModel Size=Small (28.57%), Distribution=Dist. 3, Noise Type=Asymmetric2026.0427.01
NOISYModel Size=Small (28.57%), Distribution=Dist. 3, Noise Type=Uniform2026.0426.74
NOISYModel Size=Small (28.57%), Distribution=Dist. 3, Noise Type=Systematic2026.0426.3
NOISYModel Size=Small (28.57%), Distribution=Dist. 1, Noise Type=Asymmetric2026.0425.68
NOISYModel Size=Small (28.57%), Distribution=Dist. 1, Noise Type=Uniform2026.0425.2
NOISYModel Size=Small (28.57%), Distribution=Dist. 1, Noise Type=Systematic2026.0424.92