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

Reasoning on (test) benchmark leaderboard · SOTA2 Research

Research Benchmarks

Reasoning on (test)

66ACC1o1-mini

Updated 5mo ago

Evaluation Results

Method	Links
o1-mini2024.12		66	—	9.1
4o2024.12		65	2	17.9
3.5-turbo2024.12		55	6	19.7

SOTA Paper

o1-mini

Understanding the Dark Side of LLMs' Intrinsic Self-Correction

Dataset

(test)

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Reasoning on HotPotQA Decision Making on AlfWorld Yes/No Question Answering on BoolQ (test)Programming on HumanEval (test)Programming on HumanEval