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

General LLM Evaluation research benchmarks · SOTA2 Research

General LLM Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MATH-500, MMLU-Redux, and SimpleQA (Averaged)

82.57Accuracy

53

Mar 6, 2026

Open LLM Leaderboard (test)

70.1Average Score

21

Mar 4, 2026

7.27Reasoning Score

20

Feb 26, 2026

Instruction-Following, Mathematics, and Commonsense Reasoning Combined

57Average Score

18

Mar 12, 2026

38.74Overall Score

9

Mar 4, 2026

6.66Overall Score

7

Feb 26, 2026

8.03Overall Score

7

May 28, 2026

23.1Refusal Rate

4

Feb 26, 2026

Popular datasets

MT-Bench AlignBench Open LLM Leaderboard XSTest Overall

Follow for updates

Join SOTA2 Contact