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

Language Modeling and Reasoning research benchmarks · SOTA2 Research

Language Modeling and Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

ARC-Challenge (AC), ARC-Easy (AE), HellaSwag (HS), LAMBADA-openai (LO), LAMBADA-standard (LS), PIQA (PQ), WinoGrande (WG) zero-shot

78.6Accuracy (ARC-E)

39

Jun 12, 2026

Open LLM Leaderboard

82.8ARC

33

Feb 26, 2026

Multi-benchmark Suite (AGIEval, GSM8K, MATH, Natural Questions, SimpleQA, TriviaQA, SuperGPQA) (cumulative)

90.98AGIEval (EN)

20

Mar 26, 2026

BigBench (Lamb, SQuAD, CoQA, BBH, LSAT, LangID)

24Avg Score

8

Feb 26, 2026

LLM Evaluation Suite ARC, BBH, HellaSwag, TruthfulQA, LAMBADA, WinoGrande, GSM8K, MT-Bench

54.61ARC (Accuracy)

3

Feb 26, 2026

Popular datasets

BigBench Open LLM Leaderboard LLM Evaluation Suite Multi-benchmark Suite ARC-Challenge (AC), ARC-Easy (AE), HellaSwag (HS), LAMBADA-openai (LO), LAMBADA-standard (LS), PIQA (PQ), WinoGrande (WG)

Follow for updates

Join SOTA2 Contact