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

Zero-shot language evaluation research benchmarks · SOTA2 Research

Zero-shot language evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Zero-shot NLP Evaluation Suite (WikiText2, BoolQ, PIQA, HellaSwag, WinoGrande, ARC, OBQA, MTQA) (test)

7.43WikiText2 Perplexity

27

Apr 23, 2026

Gauntlet 20 benchmarks (test)

9.2Average Normalized Accuracy

10

Mar 4, 2026

MMLU, ARC-C, PIQA, WinoG, GSM8K, HellaSwag, GPQA, RACE zero-shot

60.94Average Score

9

Feb 26, 2026

7-task evaluation suite (BoolQ, PIQA, HellaSwag, WinoGrande, ARC-E, ARC-C, OBQA) (test)

62.9BoolQ Accuracy

4

Jun 17, 2026

57.93WinoGrande

2

Mar 20, 2026

Popular datasets

Evaluation Suite DCLM NLP Evaluation Suite MMLU, ARC-C, PIQA, WinoG, GSM8K, HellaSwag, GPQA, RACE Gauntlet

Follow for updates

Join SOTA2 Contact