Benchmarking – Frontier models go out of their way to cheat (tuneloop.io)

1 points by behat 16d ago ↗ HN

0 comments

[ 0.24 ms ] story [ 2.8 ms ] thread

No comments yet.

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

Source · Live DB stats