== claude-opus-5-5 (vs bare; 10 problems) [score] prior − bare: -0.042 [-0.140, +0.054] problems up/down 2/7 [score] ace − bare: -0.131 [-0.906, +0.433] problems up/down 6/3 [score] organ_select − bare: -0.266 [-0.489, -0.085] problems up/down 1/8 [score] show_all − bare: -0.287 [-0.591, -0.089] problems up/down 0/9 [score] opus_tables_select − bare: -0.347 [-1.003, +0.232] problems up/down 2/7 [score] opus_digest_select − bare: -0.359 [-0.750, -0.068] problems up/down 1/8 [score] provenance − bare: -0.483 [-1.009, -0.092] problems up/down 1/8 [score] annotated_all − bare: -0.610 [-1.450, -0.100] problems up/down 2/8 [log1p] prior − bare: -0.036 [-0.083, -0.004] problems up/down 2/7 [log1p] ace − bare: -0.017 [-0.139, +0.066] problems up/down 7/2 [log1p] organ_select − bare: -0.064 [-0.098, -0.031] problems up/down 1/8 [log1p] show_all − bare: -0.069 [-0.105, -0.034] problems up/down 1/8 [log1p] opus_tables_select − bare: -0.050 [-0.142, +0.046] problems up/down 2/7 [log1p] opus_digest_select − bare: -0.072 [-0.117, -0.032] problems up/down 1/8 [log1p] provenance − bare: -0.095 [-0.155, -0.041] problems up/down 1/8 [log1p] annotated_all − bare: -0.121 [-0.267, -0.023] problems up/down 2/8 per-problem means (score): problem ace annotated_ bare opus_diges opus_table organ_sele prior provenance show_all L2_014 1.01 1.01 1.00 1.01 1.00 1.00 1.00 1.00 1.00 L2_022 1.31 1.04 1.34 1.16 2.65 1.03 1.25 1.04 1.03 L2_030 1.32 1.03 1.27 1.24 1.03 1.03 1.18 1.02 1.03 L2_033 1.46 1.01 1.13 1.01 1.01 1.01 1.09 1.01 1.01 L2_050 10.00 5.82 10.00 10.00 10.00 10.00 10.00 10.00 10.00 L2_061 1.04 0.94 1.04 0.94 1.03 1.03 1.03 1.03 0.94 L3_010 0.95 0.71 0.90 0.74 0.77 0.77 0.82 0.85 0.76 L3_023 0.80 1.02 0.81 0.73 0.90 0.74 0.41 0.59 0.79 L3_032 8.64 6.75 7.22 5.89 5.31 6.49 7.50 5.24 6.82 L3_040 5.26 7.68 8.38 6.78 5.90 7.33 8.37 6.47 6.84 == claude-opus-4-8 (vs bare; 10 problems) [score] opus_tables_select − bare: +0.281 [+0.111, +0.461] problems up/down 8/2 [score] annotated_all − bare: +0.271 [+0.110, +0.441] problems up/down 8/2 [score] opus_digest_select − bare: +0.263 [+0.096, +0.441] problems up/down 9/1 [score] ace − bare: +0.230 [-0.001, +0.472] problems up/down 6/4 [score] organ_select − bare: +0.224 [+0.056, +0.439] problems up/down 7/3 [score] show_all − bare: +0.216 [+0.071, +0.383] problems up/down 8/2 [score] provenance − bare: +0.185 [+0.019, +0.370] problems up/down 8/2 [score] prior − bare: -0.169 [-0.343, -0.025] problems up/down 4/5 [log1p] opus_tables_select − bare: +0.199 [+0.082, +0.322] problems up/down 8/2 [log1p] annotated_all − bare: +0.190 [+0.080, +0.306] problems up/down 8/2 [log1p] opus_digest_select − bare: +0.189 [+0.074, +0.311] problems up/down 9/1 [log1p] ace − bare: +0.164 [+0.006, +0.332] problems up/down 6/4 [log1p] organ_select − bare: +0.160 [+0.044, +0.309] problems up/down 7/3 [log1p] show_all − bare: +0.156 [+0.055, +0.270] problems up/down 8/2 [log1p] provenance − bare: +0.133 [+0.017, +0.262] problems up/down 8/2 [log1p] prior − bare: -0.118 [-0.238, -0.017] problems up/down 4/5 per-problem means (score): problem ace annotated_ bare opus_diges opus_table organ_sele prior provenance show_all L2_014 1.00 0.75 0.00 0.75 0.75 1.00 0.00 0.75 0.75 L2_022 0.61 1.03 1.03 1.03 1.03 1.03 0.78 1.03 1.04 L2_030 0.94 1.02 0.51 1.03 1.02 1.03 0.51 1.02 1.03 L2_033 0.95 0.99 0.99 1.00 0.99 0.99 0.98 1.00 0.99 L2_050 1.10 1.10 0.83 1.10 1.10 1.10 0.27 1.10 1.09 L2_061 0.99 1.02 0.99 1.02 1.02 1.02 0.26 1.02 1.02 L3_010 0.82 0.82 0.38 0.72 0.87 0.73 0.41 0.81 0.80 L3_023 0.78 0.30 0.20 0.29 0.30 0.29 0.00 0.30 0.29 L3_032 1.01 0.89 0.88 0.85 0.88 0.86 0.90 0.64 0.81 L3_040 0.04 0.71 0.12 0.78 0.79 0.11 0.12 0.12 0.28