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 Modeling research benchmarks · SOTA2 Research

General Language Modeling

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MMLU, ARC-Challenge, and CommonsenseQA Aggregate

64.77Average Score

24

Feb 26, 2026

31.1Accuracy

17

Jun 9, 2026

CodaSet OOD Average (test)

87.84Performance (%)

16

May 26, 2026

85.6Accuracy

12

May 12, 2026

General Benchmarks Llama 3.1 8B

66.5Generation Quality Score

11

Feb 26, 2026

Combined Suite (HS, PIQA, SIQA, Wino, MMLU, NQ, TQA, ARC-C, ARC-E, OBQA, BoolQ, DROP, BBH-LB, GSM8K)

57.8Accuracy

4

May 27, 2026

Overall Evaluation Suite

Qwen3-30B-A3B-Instruct-2507

73.6Average Score

4

Feb 26, 2026

BIG-Bench (test)

83.6Accuracy

2

May 12, 2026

Linguistic Task

88.9Comprehensive Score

2

Apr 10, 2026

Popular datasets

BIG-Bench LiveBench Combined Suite General Benchmarks Overall Evaluation Suite

Follow for updates

Join SOTA2 Contact