Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Multiple-choice science question answering research benchmarks · SOTA2 Research

Multiple-choice science question answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MMLU Physics Larger Dist. Shift 37, 36

32.64Accuracy

9

Feb 26, 2026

MMLU Chemistry Larger Dist. Shift 37, 36

44.79ACC

9

Feb 26, 2026

ARC-E Smaller Dist. Shift 18

76.88Accuracy

9

Feb 26, 2026

ARC-C Smaller Dist. Shift 18

69.93Accuracy

9

Feb 26, 2026

OBQA In-Distribution 64

82.73Accuracy

9

Feb 26, 2026

65Problems Evaluated

1

Jul 2, 2026

Popular datasets

MMLU ARC GPQA OBQA

Follow for updates

Join SOTA2 Contact