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

Coding on CRUX-O benchmark leaderboard · SOTA2 Research

Research Benchmarks

Coding on CRUX-O

73.39Pass@1MAPR

Updated 2mo ago

Evaluation Results

Method	Links
MAPR2025.09		73.39
GRPO2025.09		72.72

SOTA Paper

MAPR

Verifying Meta-Awareness via Predictive Rewards in Reasoning Models

Dataset

CRUX-O

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Mathematical Reasoning on AMC23 (Pass@1 and Pass@8)Mathematical Reasoning on AIME 2024 (Pass@1, Pass@8)Mathematical Reasoning on AIME '25 (Pass@1, Pass@8)Mathematical Reasoning on MATH500 (Pass@1, Pass@8)Logical Reasoning on ProofWriter (pass@1)