0

Skywork Math

Saturated

Single-turn Skywork math problems with boxed numeric answers and CoT.

Domain
rl-env
License
apache-2.0
Published
Aug 2025

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores
prime-hub
Attribution policy →

Top score 100.0% by GPT-4.1 Mini - 1 model reporting (1 frontier)

Top models

1
Skywork MathBar chart with 1 bar. Highest value: GPT-4.1 Mini at 100.
1 model

Related tools

1
View all

Implementations, trainers, datasets and scaffolds linked to this eval.

FAQ

What is Skywork Math?
Single-turn Skywork math problems with boxed numeric answers and CoT.
What is the current top score on Skywork Math?
The top reported score is 100.0% by GPT-4.1 Mini, across 1 model reporting (1 from frontier labs).
How can a model improve its Skywork Math score?
Tools linked to Skywork Math on Sophon include Skywork MATH RL Env (Prime Intellect) - RL environments, datasets, and scaffolds that target this eval.
What license is Skywork Math under?
Skywork Math is available under apache-2.0.