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 Evaluation research benchmarks · SOTA2 Research

Language Modeling Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

General Language Evaluation Suite AE, AC, SciQ, MMLU, MMLU-P, HS, OBQA, PIQA, RACE, WG, CSQA, AGI (test)

69.95AE Score

27

May 19, 2026

MMLU, GSM8k, HellaSwag, WinoGrande

72.98MMLU Accuracy

17

Mar 4, 2026

LM Evaluation Harness

60.35Accuracy

16

Apr 21, 2026

Open LLM Leaderboard

70.22ARC

14

Feb 26, 2026

6.63Grammar

5

Apr 3, 2026

Eight benchmark LLM tasks

Heterogeneous Digital-AIMC framework

49,781.23Throughput (Tokens/s)

5

Mar 4, 2026

Bolmo 1B evaluation suite

58.5Overall Average Score

5

Feb 26, 2026

ARC, HellaSwag, MMLU, TruthfulQA, WinoGrande

34.64ARC Accuracy

4

Feb 26, 2026

Popular datasets

LM Evaluation Harness Open LLM Leaderboard TinyStories LLM Tasks ARC, HellaSwag, MMLU, TruthfulQA, WinoGrande

Follow for updates

Join SOTA2 Contact