Note
Harness Tax
(65 words, 1 minute)
Across shared models, Claude Code costs about 2.0× as much as Pi and 1.6× as much as Codex on SWE-bench Lite, and 1.5× as much as Pi on Terminal-Bench 2.0, using geometric means of cost ratios. Meanwhile, the average harness effect on success rate stays within ±2% on SWE-bench Lite and within about ±5% on Terminal-Bench 2.0.
Pi kicking ass, as usual.