LLM Speedrunner: Eval for frontier models to reproduce scientific findings (github.com)

2 points by zerojames 1y ago ↗ HN

0 comments

[ 3.7 ms ] story [ 17.7 ms ] thread

No comments yet.

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

Source · Live DB stats