0

Stepfun Prover

A multi-turn RL environment for formal theorem proving in Lean 4, where models alternate between reasoning, sketching proof code, and receiving ver...

Domain
rl-env
License
unknown
Published
Mar 2026

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores
prime-hub
Attribution policy →

Top models

1
Stepfun ProverBar chart with 1 bar. Highest value: DeepSeek Prover V2 at 3.5.
1 model

Related tools

1
View all

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

FAQ

What is Stepfun Prover?
A multi-turn RL environment for formal theorem proving in Lean 4, where models alternate between reasoning, sketching proof code, and receiving ver...
How can a model improve its Stepfun Prover score?
Tools linked to Stepfun Prover on Sophon include Stepfun Prover RL Env (Prime Community) - RL environments, datasets, and scaffolds that target this eval.
What license is Stepfun Prover under?
Stepfun Prover is available under unknown.