0

Art E

ART-E: a tool-using email research RL environment for Verifiers

Domain
rl-env
License
unknown
Published
Sep 2025

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores
prime-hub
Attribution policy →

Top score 1.07 by GPT-4.1 Mini - 1 model reporting (1 frontier)

Top models

1
Art EBar chart with 1 bar. Highest value: GPT-4.1 Mini at 1.1.
1 model

Related tools

1
View all

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

FAQ

What is Art E?
ART-E: a tool-using email research RL environment for Verifiers
What is the current top score on Art E?
The top reported score is 1.07 by GPT-4.1 Mini, across 1 model reporting (1 from frontier labs).
How can a model improve its Art E score?
Tools linked to Art E on Sophon include ART E RL Env (Prime Intellect) - RL environments, datasets, and scaffolds that target this eval.
What license is Art E under?
Art E is available under unknown.