0

Apex Shortlist

MathArena Apex Shortlist final-answer evaluation environment

Open
Domain
rl-env
License
unknown
Published
May 2026
Canonical
app.primeintellect.ai/dashboard/environments/primeintellect/apex-shortlist

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores
prime-hub
Attribution policy →

Top score 86.2% by GPT-5.5 - 5 models reporting (1 frontier)

Score history

5
15%36%57%79%100%Feb 26Mar 26Apr 26Qwen3.5 397B A17BGPT-5.5

Top models

5
Apex ShortlistBar chart with 5 bars. Highest value: GPT-5.5 at 86.2.
5 models

Related tools

1
View all

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

APEX Shortlist RL Env (Prime Intellect)

Prime Intellect

Official

MathArena Apex Shortlist final-answer evaluation environment

ImplementationRL EnvMathScience

FAQ

What is Apex Shortlist?
MathArena Apex Shortlist final-answer evaluation environment
What is the current top score on Apex Shortlist?
The top reported score is 86.2% by GPT-5.5, across 5 models reporting (1 from frontier labs).
How can a model improve its Apex Shortlist score?
Tools linked to Apex Shortlist on Sophon include APEX Shortlist RL Env (Prime Intellect) - RL environments, datasets, and scaffolds that target this eval.
What license is Apex Shortlist under?
Apex Shortlist is available under unknown.