Mathematics
MathArena Platform
MathArena Platform asks models to answer research mathematics questions drawn from arXiv papers, write formal proofs in Lean that a proof checker verifies, and recognize when a stated claim is deliberately false.
422items
45subjects
MITlicense
mathematicsdomain
reasoningdomain
textmodality
item-level responses released
Saturation status: No
Response matrix
Loading session strips…
lowhighUnobserved
Scale: {0, 0.5, 1} — ArXivMath/ArXivLean use the binary subset {0,1}; BrokenArXiv adds the judge's half-credit 0.5