Study finds complex coding agent harnesses increase cost without improving performance

Research indicates that different coding agent harnesses have a negligible impact on model performance, with differences comparable to the noise from a single run. For instance, Zhipu AI's advertised 2.4-point lead over Claude Code falls within the measurement noise range. While heavier harnesses like Claude Code consume two to three times more tokens than the leanest option, pass rates remain within measurement uncertainty across the larger pool of 447 tasks, with only OpenCode showing a statistically significant deficit on this pool.