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

Math on Math 1000 samples (test) benchmark leaderboard · SOTA2 Research

Research Benchmarks

Math on Math 1000 samples (test)

75AccuracyBase Model

Updated 5mo ago

Evaluation Results

Method	Links
Base Model2026.02		75	81.3

SOTA Paper

Base Model

On-Policy Context Distillation for Language Models

Dataset

MATH

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Math on Math (test)Safety Evaluation on Safety Tweet Eval, Hatecheck, Ethos (test)Text Game on Frozen Lake (test)Text Game on Sokoban (test)Frozen Lake Evaluation on Frozen Lake 128 samples (test)