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

Examination research benchmarks · SOTA2 Research

Examination

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

61.3Score

20

Feb 26, 2026

55MMLU Score

20

Feb 26, 2026

82.8Accuracy

10

Feb 26, 2026

Qwen3-VL Thinking

0.771Score

9

Mar 11, 2026

LiveBench 2024-11-25

Qwen3-VL Thinking

70.79Score

5

Feb 26, 2026

50.38Score

5

Feb 26, 2026

70.83Score

5

Feb 26, 2026

Popular datasets

MMLU GPQA CMMLU GaoKao LiveBench

Follow for updates

Join SOTA2 Contact