MathArena: Evaluating LLMs on uncontaminated math questions (matharena.ai)

2 points by GaggiX 7mo ago ↗ HN

0 comments

[ 3.7 ms ] story [ 11.0 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats