Benchmark that evaluates LLMs using 759 NYT Connections puzzles (github.com)

1 points by ShrugLife 9mo ago ↗ HN

0 comments

[ 9.1 ms ] story [ 39.9 ms ] thread

No comments yet.

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

Source · Live DB stats