Comment by eru
2 months ago
Hmm, Claude 4 (with extended thinking) seems a lot worse than Gemini 2.5 Pro and ChatGPT o3 at solving algorithmic programming problems.
2 months ago
Hmm, Claude 4 (with extended thinking) seems a lot worse than Gemini 2.5 Pro and ChatGPT o3 at solving algorithmic programming problems.
No comments yet
Contribute on Hacker News ↗