Skip to content
Evaluation sources

MathArena · ArXivLean

MathArena / ETH Zurich / Reasoning · Verifies mathematical proofs in Lean

Official evaluation
Across NexGateHub AI News Observing
Evidence budgetNot scored
Upstream data timeUnverified
Last successful syncCollection has not started

What it measures and how

Uses raw results for individual test sets and versions, excluding the Expected performance aggregate fitted across question sets.

How this evidence is used

Under review: redisplay terms remain unclear; results are not collected for official scoring.

Evaluation limits & attribution

Under review: redisplay terms remain unclear; results are not collected for official scoring.

Data license: Code is MIT. Data includes CC BY-NC-SA 4.0 restrictions; task data and leaderboard results must be distinguished.

Results are published by MathArena / ETH Zurich. Original scores and the NexGateHub consensus index use different scales and cannot be added directly.