Comment by kgeist
6 hours ago
The benchmark is strange: single-run results (the author acknowledges it's unreliable) and uses older models like GPT-4o or Opus 4 (although the benchmark is from 2026).
6 hours ago
The benchmark is strange: single-run results (the author acknowledges it's unreliable) and uses older models like GPT-4o or Opus 4 (although the benchmark is from 2026).
No comments yet
Contribute on Hacker News ↗