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 Downstream Task Evaluation research benchmarks · SOTA2 Research

Zero-shot Downstream Task Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

ARC-c, ARC-e, WinoGrande, BoolQ, HellaSwag, OpenBookQA, PIQA, MMLU standard (test val)

0.736Average Accuracy

88

Feb 26, 2026

LM-EVAL (Average of HellaSwag, PIQA, ARC-Easy, ARC-Challenge, and WinoGrande) zero-shot latest

76Average Accuracy

30

Feb 26, 2026

ARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE, SocialIQA, SciQ, SWAG

77.9ARC-e Accuracy

12

Feb 26, 2026

Zero-shot LM Evaluation Suite (MMLU, HellaSwag, WinoGrande, PIQA, ARC-E, ARC-C, OBQA)

59.8MMLU

6

Jun 4, 2026

Downstream Tasks zero-shot (Arc-c, Arc-e, BoolQ, COPA, MMLU, OBQA, PIQA, RTE, Winogrande)

49.32Arc-c

6

Feb 26, 2026

Downstream Evaluation Suite (Arc-e, PIQA, Hellaswag, OpenBookQA, Winogrande, MMLU, BoolQ)

53.83Arc-e

4

Feb 26, 2026

Popular datasets

Downstream Tasks LM Eval ARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE, SocialIQA, SciQ, SWAG ARC, WinoGrande, BoolQ, HellaSwag, OpenBookQA, PIQA, MMLU Downstream Evaluation Suite

Follow for updates

Join SOTA2 Contact