Is GPT-5.6 Sol Max Worth It?

I ran some tests with GPT-5.6 Sol in max reasoning on both Codex CLI and my own agent harness: https://github.com/Tura-AI/tura. I tested only one task and the token efficiency difference is not as great as in high mode: Tura used up to 83.1% fewer turns on the rewrite benchmark and improved the harness results by 7 percentage points. In ultra, the difference is around 50% and increased harness result only by one.

Full report: https://turaai.net/blog#is-gpt-5-6-sol-max-worth-it

However, in the bug fixing tasks based on the published report from DeepSWE and others, the performance increase is less impressive compared with the increase in costs. Here is the summary:

Use Max for building new projects, and high for debugging or adding defined features.