Hacker News

Favorites Setup
Comment by chvid | original | Hy4 preview
[−]chvid · 2026-08-30 Sun 06:18 UTC · link
This is a remarkable coherent and clear reasoning trace.

Maybe you should start also comparing reasoning traces when you do your pelican benchmark.

[−]armcat · 2026-08-30 Sun 06:34 UTC · link
That would be very interesting but only the open models allow you to see the reasoning trace
[−]kmike84 · 2026-08-30 Sun 11:27 UTC · link
So, open models will be better on this benchmark, which is deserved