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

Next Step Generation research benchmarks · SOTA2 Research

Next Step Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

PeanoBench 21 incorrect proofs

3.7Accuracy

4

Mar 5, 2026

Human Evaluation Subset

CoP (Qwen2.5-VL-7B)

65Win Rate

2

May 15, 2026

Popular datasets

Human Evaluation PeanoBench

Follow for updates

Join SOTA2 Contact