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 Understanding and Reasoning research benchmarks · SOTA2 Research

Zero-shot Language Understanding and Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

BENCH-PROXY (MMLU, ANLI, HellaSwag, PIQA, SIQA, W.G., ARC-E, ARC-C, C.QA, WSC) (test)

34.32MMLU

24

Feb 26, 2026

LLM Evaluation Suite (MMLU, ARC-C, PIQA, WinoG, GSM8K, HellaSwag, GPQA, RACE) zero-shot LLaDA1.5

58.59Average Score

13

Feb 26, 2026

LLM Evaluation Suite (HellaSwag, MMLU, ARC-C, BoolQ, Lambada, ARC-E, HumanEval) zero-shot Qwen3-30B-A3B

79.8HellaSwag Accuracy

12

Apr 2, 2026

nine-benchmark suite (MMLU, ARC, CSQA, HellaSwag, OpenBookQA, PIQA, SocialIQA, WinoGrande) (test val)

31.7MMLU Accuracy

6

Mar 17, 2026

Popular datasets

LLM Evaluation Suite BENCH-PROXY nine-benchmark suite

Follow for updates

Join SOTA2 Contact