The comparison between harnesses is very nice. Interesting to see that using a different harness can bump the performance of the model as much as a new version (e.g., GPT 5.5+Codex ~= GPT 5.6+Terminus, at lower cost)
The comparison between harnesses is very nice. Interesting to see that using a different harness can bump the performance of the model as much as a new version (e.g., GPT 5.5+Codex ~= GPT 5.6+Terminus, at lower cost)