0

Reasoning Core Env

Formally verifiable reasoning on general symbolic domains (planning, logic, math...) with procedurally generated data.

Domain
rl-env
License
unknown
Published
Sep 2025

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores
prime-hub
Attribution policy →

Top score 46.8% by GPT-4.1 Mini - 1 model reporting (1 frontier)

Top models

1
Reasoning Core EnvBar chart with 1 bar. Highest value: GPT-4.1 Mini at 46.8.
1 model

Related tools

1
View all

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

FAQ

What is Reasoning Core Env?
Formally verifiable reasoning on general symbolic domains (planning, logic, math...) with procedurally generated data.
What is the current top score on Reasoning Core Env?
The top reported score is 46.8% by GPT-4.1 Mini, across 1 model reporting (1 from frontier labs).
How can a model improve its Reasoning Core Env score?
Tools linked to Reasoning Core Env on Sophon include CORE ENV RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
What license is Reasoning Core Env under?
Reasoning Core Env is available under unknown.