Hacker News new | ask | show | jobs
by Szpadel 23 days ago
sources for easy confirmation:

https://github.com/openai/codex/blob/98d28aab54ed86714901b66...

https://github.com/openai/codex/blob/98d28aab54ed86714901b66...

https://github.com/openai/codex/blob/98d28aab54ed86714901b66...
1 comments
cactusplant7374 23 days ago
Very strange because in the TerminalBench benchmark Ultra does better than Sol. They didn’t add the reasoning level to the chart.
link