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

Procedural reasoning research benchmarks · SOTA2 Research

Procedural reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

46.6BertScore

10

May 15, 2026

61.4BertScore

10

May 15, 2026

Procedural-skill v1.0 (test)

pre-SFT Haiku-4-5

95.5Performance Score (BL)

7

May 13, 2026

Popular datasets

RecipeQA Procedural-skill ProcedureVQA

Follow for updates

Join SOTA2 Contact