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 Capability research benchmarks · SOTA2 Research

General Language Capability

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MMLU, GSM8K, HEval, IFEval, MTBench

76.4MMLU Accuracy

16

Jul 2, 2026

Aggregate K&R, IFEval-PT, HumanEval

Tucano2-qwen-3.7B-Instruct

53.64Average Score

14

Mar 5, 2026

Aggregate IFEval, IFBench, Arena-Hard-v2.0, Creative Writing v3, WritingBench

71.9Average Score

11

May 29, 2026

DCLM CORE v2 (test)

61.9Commonsense Score

7

Jun 11, 2026

General Capability Suite (MMLU, GSM8K, GPQA)

73.6MMLU Accuracy

5

May 12, 2026

BIG-bench 57 Task

48.7Accuracy (Weighted)

5

Feb 26, 2026

Popular datasets

Aggregate BIG-Bench DCLM General Capability Suite MMLU, GSM8K, HEval, IFEval, MTBench

Follow for updates

Join SOTA2 Contact