Aime25

Fresh

AIME 2025 competition math (single-turn eval, math-verify scoring).

Type: RL Env
Publisher: Prime Intellect
Tags: V1
Runtime: single-turn
License: unknown
Size: v0.1.0
Published: Jul 2026
Updated: Sep 2026
Canonical: app.primeintellect.ai/dashboard/environments/primeintellect/aime25

Cite

Notes

Only stored in your browser.

Attribution

README: api.primeintellect.ai/api/v1/environmentshub/primeintellect/aime25/@0.1.0/inspect

Attribution policy →

aime25

AIME 2025 competition math tasks (parts I and II). The model reasons through each task and boxes an integer answer, scored by math equivalence (math-verify) of the boxed answer against the gold.

Taskset

Source: opencompass/AIME2025
Size: 30 tasks (AIME2025-I and AIME2025-II combined)

Changelog

2026-08-31: Yield task records on demand so bounded evaluations construct only the requested prefix.
2026-06-23: Initial v1 taskset.