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 Language Evaluation research benchmarks · SOTA2 Research

General Language Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

14-Benchmark Evaluation Suite

Qwen-2.5-7B-TuluSFT

62.05Average Score

72

Mar 4, 2026

Aggregated MMLU, BoolQ, OpenBookQA, RTE

70.4Average Accuracy

42

Apr 9, 2026

5 Datasets Zero-shot

72.87Average Accuracy

33

Feb 26, 2026

English lm-evaluation-harness

0.819ARC Easy Acc (Norm)

16

Apr 20, 2026

Aggregated Benchmarks

Qwen3-14B + NGM

0.745Average Score

10

May 19, 2026

Open LLM Leaderboard 1

66.12Overall Score

9

Mar 4, 2026

12 general benchmarks Avg

+ Midtrain (100B)

68.24General Average Score

3

Apr 10, 2026

OLMo-2 Held-out Evals

24.4AGIEval Score

2

Mar 4, 2026

Popular datasets

Open LLM Leaderboard 5-Datasets English Aggregated General Benchmarks

Follow for updates

Join SOTA2 Contact