1 model n_runs acceptance_taskw det_completion critical_error_rate quality_mean cost_mean cost_per_accepted wall_median_s tool_calls_mean timeout_rate20 fable 20 0.85 0.95 0.05 86.938 2.805 3.300 397.60 21.90 0.031 opus 30 0.90 1.00 0.00 85.694 0.906 1.006 218.80 17.20 0.042 sonnet 20 0.85 1.00 0.00 80.896 0.341 0.401 131.05 13.45 0.05 contrast outcome estimate ci_lo ci_hi perm_p J60 sonnet-opus S -0.050 -0.150 0.000 1.000 1071 sonnet-opus D 0.000 0.000 0.000 1.000 1082 sonnet-opus quality -4.799 -6.702 -2.965 0.002 1093 sonnet-opus C -0.564 -0.678 -0.465 0.001 10104 fable-opus S -0.050 -0.150 0.000 1.000 10115 fable-opus D -0.050 -0.150 0.000 1.000 10126 fable-opus quality 1.243 -1.375 3.840 0.404 10137 fable-opus C 1.899 1.563 2.306 0.002 1014