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

Code Agent research benchmarks · SOTA2 Research

Code Agent

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

SWE-Bench Verified

Claude Opus 4.5

0.809Score

21

Jul 2, 2026

Terminal-Bench Hard

57.6Score

12

Mar 31, 2026

Popular datasets

SWE-Bench Terminal-bench

Follow for updates

Join SOTA2 Contact