0

Arxivmath

Fresh

MathArena research-level math from arXiv papers (bring your own web search), scored by math-verify on the boxed answer.

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/arxivmath

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →

arxivmath

MathArena research-level math tasks extracted from arXiv papers, each with a verifiable final answer. The taskset ships only the tasks and scoring (no search tool), so the agent must bring its own web search; scored by math equivalence (math-verify) of the boxed answer against the gold.

Taskset

Changelog

  • 2026-08-31: Yield task records on demand so bounded evaluations construct only the requested prefix.
  • 2026-07-02: Initial v1 taskset.