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

Expert-Level Reasoning research benchmarks · SOTA2 Research

Expert-Level Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

84.3Pass@1 Score

20

Jul 7, 2026

Humanity's Last Exam 2,158 text-only

54.2Avg@3 Score

15

Mar 18, 2026

HLE (Humanity's Last Exam) text-only subset (val)

52.2Inference Accuracy

13

Feb 26, 2026

XBench-DeepSearch 1.0 (test)

0.9Inference Accuracy

12

Feb 26, 2026

GAIA text-only (val)

81.6Inference Accuracy

12

Feb 26, 2026

26.5Accuracy (HLE)

5

Jul 7, 2026

Popular datasets

GPQA GAIA Humanity's Last Exam HLE xbench

Follow for updates

Join SOTA2 Contact