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 Understanding research benchmarks – Page 3 · SOTA2 Research

General Language Understanding

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

7.576Average Accepted Length (m)

4

May 28, 2026

26.32CORE Score

4

May 22, 2026

AI2 OLMES (test)

40.4ARC-E Accuracy

4

May 12, 2026

General Benchmarks (MMLU, AlpacaEval, Arena-Hard)

Qwen2.5-7B + DataFlow-Chat-15K

73.41MMLU Accuracy

4

Feb 26, 2026

73Accuracy

4

Feb 26, 2026

52.6Score

4

Feb 26, 2026

73.3Score

4

Feb 26, 2026

64Score

4

Feb 26, 2026

GPT-3 Evaluation Suite (11 tasks: HellaSwag, LAMBADA, TriviaQA, WebQs, Winogrande, PIQA, ARC Challenge, ARC Easy, ANLI R1, ANLI R2, ANLI R3) zero-shot

GPT-3 125M (Original)

33.6Average Accuracy

4

Feb 26, 2026

Chinese Grouped General-Purpose Metrics

81.79Chinese Accuracy

3

Jun 19, 2026

English Grouped General-Purpose Metrics

61.96Accuracy (English)

3

Jun 19, 2026

48.09Throughput (Tokens/sec)

3

May 28, 2026

83.6Performance

3

May 12, 2026

Turkish Non-Retrieval Tasks Consolidated

81.8Overall Accuracy

3

Feb 26, 2026

90.61Accuracy

3

Feb 26, 2026

0.925Accuracy

3

Feb 26, 2026

MMLU-Redux 5-shot

92.19Accuracy

3

Feb 26, 2026

80.22Accuracy

3

Feb 26, 2026

93.92Accuracy

3

Feb 26, 2026

MMLU-Pro 5-shot

75.58Accuracy

3

Feb 26, 2026

Page 3 of 3

Popular datasets

MMLU Open LLM Leaderboard GLUE BIG-Bench C-Eval

Follow for updates

Join SOTA2 Contact