run_id,judge_idx,judge_model,score,scores,cost_usd,judged_utc HR-01_A3_r2_sonnet,0,claude-opus-5-5,72.5,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 3, ""workbook_usability"": 3}, ""acceptable"": false}",0.123031,2026-11-03T01:22:33.887996Z HR-01_A3_r2_sonnet,1,claude-sonnet-5-5,76.25,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 4, ""workbook_usability"": 3}, ""acceptable"": false}",0.059088,2026-11-03T01:22:39.612216Z HR-01_A3_r2_sonnet,2,claude-sonnet-5-5,76.25,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 4, ""workbook_usability"": 3}, ""acceptable"": false}",0.0572222,2026-11-03T01:22:48.720177Z FIN-01_A3_r2_sonnet,0,claude-opus-5-5,75.0,"{""scores"": {""model_integrity"": 3, ""discount_rate"": 3, ""balance_sheet_judgement"": 3, ""memo_quality"": 3, ""independent_judgement"": 3, ""completeness_and_disclosure"": 3}, ""acceptable"": true}",0.105241,2026-11-03T01:21:54.533643Z FIN-01_A3_r2_sonnet,1,claude-sonnet-5-5,78.75,"{""scores"": {""model_integrity"": 3, ""discount_rate"": 3, ""balance_sheet_judgement"": 4, ""memo_quality"": 3, ""independent_judgement"": 3, ""completeness_and_disclosure"": 3}, ""acceptable"": true}",0.04149050000000001,2026-11-03T01:21:59.756779Z FIN-01_A3_r2_sonnet,2,claude-sonnet-5-5,78.75,"{""scores"": {""model_integrity"": 3, ""discount_rate"": 3, ""balance_sheet_judgement"": 4, ""memo_quality"": 3, ""independent_judgement"": 3, ""completeness_and_disclosure"": 3}, ""acceptable"": true}",0.040840499999999995,2026-11-03T01:22:06.196724Z ACC-01_A3_r2_sonnet,0,claude-opus-5-5,93.75,"{""scores"": {""reconciliation_mechanics"": 3, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 4, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.10823479999999999,2026-11-03T01:23:39.963017Z ACC-01_A3_r2_sonnet,1,claude-sonnet-5-5,91.25,"{""scores"": {""reconciliation_mechanics"": 3, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 4, ""report_quality"": 3, ""professional_judgement"": 4}, ""acceptable"": true}",0.0441224,2026-11-03T01:23:45.297581Z ACC-01_A3_r2_sonnet,2,claude-sonnet-5-5,91.25,"{""scores"": {""reconciliation_mechanics"": 3, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 4, ""report_quality"": 3, ""professional_judgement"": 4}, ""acceptable"": true}",0.0439099,2026-11-03T01:23:51.099894Z ADM-01_A3_r1_sonnet,0,claude-opus-5-5,56.25,"{""scores"": {""prioritisation"": 3, ""replies"": 0, ""calendar"": 4, ""briefing"": 3, ""filing"": 0, ""risk_handling"": 3}, ""acceptable"": false}",0.113901,2026-11-03T01:24:51.748176Z ADM-01_A3_r1_sonnet,1,claude-sonnet-5-5,70.0,"{""scores"": {""prioritisation"": 3, ""replies"": 1, ""calendar"": 4, ""briefing"": 4, ""filing"": 0, ""risk_handling"": 4}, ""acceptable"": false}",0.051123,2026-11-03T01:24:58.032740Z ADM-01_A3_r1_sonnet,2,claude-sonnet-5-5,66.25,"{""scores"": {""prioritisation"": 3, ""replies"": 1, ""calendar"": 4, ""briefing"": 4, ""filing"": 0, ""risk_handling"": 3}, ""acceptable"": false}",0.0493738,2026-11-03T01:25:03.629056Z ACC-01_A3_r1_sonnet,0,claude-opus-5-5,100.0,"{""scores"": {""reconciliation_mechanics"": 4, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 4, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.14066599999999999,2026-11-03T01:23:07.771499Z ACC-01_A3_r1_sonnet,1,claude-sonnet-5-5,90.0,"{""scores"": {""reconciliation_mechanics"": 3, ""discrepancy_detection"": 4, ""correcting_entries"": 3, ""cash_position"": 4, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.06422800000000001,2026-11-03T01:23:13.240050Z ACC-01_A3_r1_sonnet,2,claude-sonnet-5-5,90.0,"{""scores"": {""reconciliation_mechanics"": 3, ""discrepancy_detection"": 4, ""correcting_entries"": 3, ""cash_position"": 4, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.0626924,2026-11-03T01:23:19.108166Z BANK-01_A3_r1_sonnet,0,claude-opus-5-5,97.5,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 4, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 4, ""spreadsheet_quality"": 3}, ""acceptable"": true}",0.12998099999999999,2026-11-03T01:25:46.257972Z BANK-01_A3_r1_sonnet,1,claude-sonnet-5-5,82.5,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 3, ""risk_identification"": 4, ""structuring_and_security"": 3, ""memo_professionalism"": 3, ""spreadsheet_quality"": 2}, ""acceptable"": true}",0.055903,2026-11-03T01:25:52.085635Z BANK-01_A3_r1_sonnet,2,claude-sonnet-5-5,86.25,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 3, ""risk_identification"": 4, ""structuring_and_security"": 3, ""memo_professionalism"": 4, ""spreadsheet_quality"": 2}, ""acceptable"": true}",0.0539709,2026-11-03T01:25:57.376092Z ADM-01_A3_r2_sonnet,0,claude-opus-5-5,56.25,"{""scores"": {""prioritisation"": 3, ""replies"": 0, ""calendar"": 4, ""briefing"": 3, ""filing"": 0, ""risk_handling"": 3}, ""acceptable"": false}",0.10609759999999999,2026-11-03T01:27:33.889312Z ADM-01_A3_r2_sonnet,1,claude-sonnet-5-5,61.25000000000001,"{""scores"": {""prioritisation"": 3, ""replies"": 1, ""calendar"": 4, ""briefing"": 3, ""filing"": 0, ""risk_handling"": 3}, ""acceptable"": false}",0.0472213,2026-11-03T01:27:39.868965Z ADM-01_A3_r2_sonnet,2,claude-sonnet-5-5,61.25000000000001,"{""scores"": {""prioritisation"": 3, ""replies"": 1, ""calendar"": 4, ""briefing"": 3, ""filing"": 0, ""risk_handling"": 3}, ""acceptable"": false}",0.0473513,2026-11-03T01:27:45.640908Z RE-01_A3_r2_sonnet,0,claude-opus-5-5,95.0,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 3, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 4, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.0971176,2026-11-03T01:26:23.689347Z RE-01_A3_r2_sonnet,1,claude-sonnet-5-5,95.0,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 3, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 4, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.0404213,2026-11-03T01:26:29.934585Z RE-01_A3_r2_sonnet,2,claude-sonnet-5-5,91.25,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 3, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 3, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.040253800000000006,2026-11-03T01:26:35.392394Z RE-01_A3_r1_sonnet,0,claude-opus-5-5,81.25,"{""scores"": {""comparable_selection"": 3, ""adjustment_grid"": 2, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 3, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": false}",0.1047626,2026-11-03T01:27:57.690870Z RE-01_A3_r1_sonnet,1,claude-sonnet-5-5,91.25,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 3, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 3, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.0421188,2026-11-03T01:28:02.965341Z RE-01_A3_r1_sonnet,2,claude-sonnet-5-5,91.25,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 3, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 3, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.042686299999999996,2026-11-03T01:28:12.596979Z HR-01_A3_r1_sonnet,0,claude-opus-5-5,72.5,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 3, ""workbook_usability"": 3}, ""acceptable"": false}",0.1192994,2026-11-03T01:29:08.717574Z HR-01_A3_r1_sonnet,1,claude-sonnet-5-5,72.5,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 3, ""workbook_usability"": 3}, ""acceptable"": false}",0.05420219999999999,2026-11-03T01:29:14.243685Z HR-01_A3_r1_sonnet,2,claude-sonnet-5-5,68.75,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 3, ""correspondence"": 0, ""summary_clarity"": 3, ""workbook_usability"": 3}, ""acceptable"": false}",0.05359219999999999,2026-11-03T01:29:19.236004Z RES-01_A3_r2_sonnet,0,claude-opus-5-5,71.25,"{""scores"": {""cleaning_log"": 3, ""specification_fidelity"": 4, ""tables_figure"": 2, ""reference_check"": 4, ""report_quality"": 3, ""reproducibility"": 0, ""professional_judgement"": 2}, ""acceptable"": false}",0.24240040000000002,2026-11-03T01:29:07.737833Z RES-01_A3_r2_sonnet,1,claude-sonnet-5-5,78.75,"{""scores"": {""cleaning_log"": 3, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 3, ""report_quality"": 3, ""reproducibility"": 2, ""professional_judgement"": 4}, ""acceptable"": true}",0.11448269999999999,2026-11-03T01:29:14.636789Z RES-01_A3_r2_sonnet,2,claude-sonnet-5-5,78.75,"{""scores"": {""cleaning_log"": 4, ""specification_fidelity"": 3, ""tables_figure"": 3, ""reference_check"": 3, ""report_quality"": 3, ""reproducibility"": 2, ""professional_judgement"": 4}, ""acceptable"": true}",0.1143077,2026-11-03T01:29:21.905256Z LEGAL-01_A3_r2_sonnet,0,claude-opus-5-5,91.25,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 3, ""open_items"": 4, ""presentation"": 4}, ""acceptable"": true}",0.09859140000000001,2026-11-03T01:30:51.401238Z LEGAL-01_A3_r2_sonnet,1,claude-sonnet-5-5,88.75,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 3, ""open_items"": 4, ""presentation"": 3}, ""acceptable"": true}",0.0399982,2026-11-03T01:30:57.030486Z LEGAL-01_A3_r2_sonnet,2,claude-sonnet-5-5,88.75,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 3, ""open_items"": 4, ""presentation"": 3}, ""acceptable"": true}",0.0394582,2026-11-03T01:31:02.795742Z PROC-01_A3_r1_sonnet,0,claude-opus-5-5,91.25,"{""scores"": {""compliance_screening"": 4, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 3, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 4}, ""acceptable"": true}",0.10125100000000001,2026-11-03T01:30:53.754408Z PROC-01_A3_r1_sonnet,1,claude-sonnet-5-5,85.0,"{""scores"": {""compliance_screening"": 3, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 3, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 3}, ""acceptable"": true}",0.042672999999999996,2026-11-03T01:31:00.300736Z PROC-01_A3_r1_sonnet,2,claude-sonnet-5-5,85.0,"{""scores"": {""compliance_screening"": 3, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 3, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 3}, ""acceptable"": true}",0.040834,2026-11-03T01:31:05.259976Z BANK-01_A3_r2_sonnet,0,claude-opus-5-5,97.5,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 4, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 4, ""spreadsheet_quality"": 3}, ""acceptable"": true}",0.12661680000000003,2026-11-03T01:33:26.850698Z BANK-01_A3_r2_sonnet,1,claude-sonnet-5-5,86.25,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 3, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 3, ""spreadsheet_quality"": 2}, ""acceptable"": true}",0.04826090000000001,2026-11-03T01:33:33.065176Z BANK-01_A3_r2_sonnet,2,claude-sonnet-5-5,86.25,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 3, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 3, ""spreadsheet_quality"": 2}, ""acceptable"": true}",0.0477484,2026-11-03T01:33:39.311685Z RES-01_A3_r1_sonnet,0,claude-opus-5-5,70.0,"{""scores"": {""cleaning_log"": 3, ""specification_fidelity"": 3, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 3, ""reproducibility"": 0, ""professional_judgement"": 2}, ""acceptable"": false}",0.23748539999999999,2026-11-03T01:32:46.575915Z RES-01_A3_r1_sonnet,1,claude-sonnet-5-5,82.5,"{""scores"": {""cleaning_log"": 3, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 3, ""reproducibility"": 2, ""professional_judgement"": 4}, ""acceptable"": true}",0.1124152,2026-11-03T01:32:52.882363Z RES-01_A3_r1_sonnet,2,claude-sonnet-5-5,80.0,"{""scores"": {""cleaning_log"": 3, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 3, ""reproducibility"": 1, ""professional_judgement"": 4}, ""acceptable"": true}",0.1123102,2026-11-03T01:32:59.377232Z LEGAL-01_A3_r1_sonnet,0,claude-opus-5-5,95.0,"{""scores"": {""coverage"": 4, ""calibration"": 4, ""redlines"": 4, ""memo"": 3, ""open_items"": 4, ""presentation"": 4}, ""acceptable"": true}",0.10268639999999998,2026-11-03T01:35:10.540630Z LEGAL-01_A3_r1_sonnet,1,claude-sonnet-5-5,88.75,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 3, ""open_items"": 4, ""presentation"": 3}, ""acceptable"": true}",0.04512070000000001,2026-11-03T01:35:16.730576Z LEGAL-01_A3_r1_sonnet,2,claude-sonnet-5-5,88.75,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 3, ""open_items"": 4, ""presentation"": 3}, ""acceptable"": true}",0.04501070000000001,2026-11-03T01:35:22.817990Z BI-01_A3_r1_sonnet,0,claude-opus-5-5,62.5,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 2, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 1, ""R6_professional_conduct"": 1}, ""acceptable"": false}",0.1072388,2026-11-03T01:36:01.268132Z BI-01_A3_r1_sonnet,1,claude-sonnet-5-5,62.5,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 2, ""R3_commentary"": 3, ""R4_data_quality"": 2, ""R5_methodology_reproducibility"": 2, ""R6_professional_conduct"": 3}, ""acceptable"": false}",0.0485069,2026-11-03T01:36:08.275988Z BI-01_A3_r1_sonnet,2,claude-sonnet-5-5,72.5,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 3, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 2, ""R6_professional_conduct"": 3}, ""acceptable"": true}",0.0474619,2026-11-03T01:36:14.184947Z FIN-01_A3_r1_sonnet,0,claude-opus-5-5,83.75,"{""scores"": {""model_integrity"": 3, ""discount_rate"": 3, ""balance_sheet_judgement"": 3, ""memo_quality"": 4, ""independent_judgement"": 4, ""completeness_and_disclosure"": 3}, ""acceptable"": true}",0.096361,2026-11-03T01:36:27.703523Z FIN-01_A3_r1_sonnet,1,claude-sonnet-5-5,82.5,"{""scores"": {""model_integrity"": 3, ""discount_rate"": 3, ""balance_sheet_judgement"": 4, ""memo_quality"": 3, ""independent_judgement"": 4, ""completeness_and_disclosure"": 3}, ""acceptable"": true}",0.041417999999999996,2026-11-03T01:36:34.022779Z FIN-01_A3_r1_sonnet,2,claude-sonnet-5-5,78.75,"{""scores"": {""model_integrity"": 3, ""discount_rate"": 3, ""balance_sheet_judgement"": 3, ""memo_quality"": 3, ""independent_judgement"": 4, ""completeness_and_disclosure"": 3}, ""acceptable"": true}",0.0402755,2026-11-03T01:36:38.983813Z PROC-01_A3_r2_sonnet,0,claude-opus-5-5,85.0,"{""scores"": {""compliance_screening"": 4, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 2, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 3}, ""acceptable"": true}",0.106268,2026-11-03T01:37:29.164308Z PROC-01_A3_r2_sonnet,1,claude-sonnet-5-5,85.0,"{""scores"": {""compliance_screening"": 3, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 3, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 3}, ""acceptable"": true}",0.0415015,2026-11-03T01:37:35.450831Z PROC-01_A3_r2_sonnet,2,claude-sonnet-5-5,85.0,"{""scores"": {""compliance_screening"": 3, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 3, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 3}, ""acceptable"": true}",0.0410865,2026-11-03T01:37:45.274976Z BI-01_A3_r2_sonnet,0,claude-opus-5-5,67.5,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 3, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 1, ""R6_professional_conduct"": 1}, ""acceptable"": false}",0.1014338,2026-11-03T01:38:44.417494Z BI-01_A3_r2_sonnet,1,claude-sonnet-5-5,72.5,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 3, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 2, ""R6_professional_conduct"": 3}, ""acceptable"": true}",0.0432169,2026-11-03T01:38:50.113264Z BI-01_A3_r2_sonnet,2,claude-sonnet-5-5,72.5,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 3, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 2, ""R6_professional_conduct"": 3}, ""acceptable"": true}",0.0433669,2026-11-03T01:38:59.093082Z RES-01_A3_r1_fable,0,claude-opus-5-5,85.0,"{""scores"": {""cleaning_log"": 4, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 4, ""reproducibility"": 0, ""professional_judgement"": 3}, ""acceptable"": false}",0.25351599999999996,2026-11-03T01:25:44.728417Z RES-01_A3_r1_fable,1,claude-sonnet-5-5,93.75,"{""scores"": {""cleaning_log"": 4, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 4, ""reproducibility"": 3, ""professional_judgement"": 4}, ""acceptable"": true}",0.122903,2026-11-03T01:25:51.179427Z RES-01_A3_r1_fable,2,claude-sonnet-5-5,93.75,"{""scores"": {""cleaning_log"": 4, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 4, ""reproducibility"": 3, ""professional_judgement"": 4}, ""acceptable"": true}",0.12162269999999999,2026-11-03T01:25:57.813045Z FIN-01_A3_r1_fable,0,claude-opus-5-5,88.75,"{""scores"": {""model_integrity"": 4, ""discount_rate"": 3, ""balance_sheet_judgement"": 3, ""memo_quality"": 4, ""independent_judgement"": 3, ""completeness_and_disclosure"": 4}, ""acceptable"": true}",0.129606,2026-11-03T01:25:51.335951Z FIN-01_A3_r1_fable,1,claude-sonnet-5-5,87.5,"{""scores"": {""model_integrity"": 4, ""discount_rate"": 3, ""balance_sheet_judgement"": 4, ""memo_quality"": 3, ""independent_judgement"": 3, ""completeness_and_disclosure"": 4}, ""acceptable"": true}",0.0559855,2026-11-03T01:25:56.932053Z FIN-01_A3_r1_fable,2,claude-sonnet-5-5,87.5,"{""scores"": {""model_integrity"": 4, ""discount_rate"": 3, ""balance_sheet_judgement"": 4, ""memo_quality"": 3, ""independent_judgement"": 3, ""completeness_and_disclosure"": 4}, ""acceptable"": true}",0.05669049999999999,2026-11-03T01:26:04.131992Z PROC-01_A3_r2_fable,0,claude-opus-5-5,100.0,"{""scores"": {""compliance_screening"": 4, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 4, ""workbook_quality"": 4, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 4}, ""acceptable"": true}",0.14819100000000002,2026-11-03T01:25:21.359581Z PROC-01_A3_r2_fable,1,claude-sonnet-5-5,92.5,"{""scores"": {""compliance_screening"": 4, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 4, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 3}, ""acceptable"": true}",0.06387300000000001,2026-11-03T01:25:27.456703Z PROC-01_A3_r2_fable,2,claude-sonnet-5-5,95.0,"{""scores"": {""compliance_screening"": 4, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 4, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 4}, ""acceptable"": true}",0.062344000000000004,2026-11-03T01:25:33.238638Z ACC-01_A3_r1_fable,0,claude-opus-5-5,100.0,"{""scores"": {""reconciliation_mechanics"": 4, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 4, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.1593848,2026-11-03T01:28:29.008308Z ACC-01_A3_r1_fable,1,claude-sonnet-5-5,100.0,"{""scores"": {""reconciliation_mechanics"": 4, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 4, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.07277739999999999,2026-11-03T01:28:35.234033Z ACC-01_A3_r1_fable,2,claude-sonnet-5-5,96.25,"{""scores"": {""reconciliation_mechanics"": 4, ""discrepancy_detection"": 4, ""correcting_entries"": 3, ""cash_position"": 4, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.07191739999999999,2026-11-03T01:28:44.350211Z HR-01_A3_r1_fable,0,claude-opus-5-5,72.5,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 3, ""workbook_usability"": 3}, ""acceptable"": false}",0.1401894,2026-11-03T01:26:59.370814Z HR-01_A3_r1_fable,1,claude-sonnet-5-5,78.75,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 4, ""workbook_usability"": 4}, ""acceptable"": false}",0.0664447,2026-11-03T01:27:04.112895Z HR-01_A3_r1_fable,2,claude-sonnet-5-5,72.5,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 3, ""correspondence"": 0, ""summary_clarity"": 4, ""workbook_usability"": 3}, ""acceptable"": false}",0.0667947,2026-11-03T01:27:09.798095Z RE-01_A3_r2_fable,0,claude-opus-5-5,100.0,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 4, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 4, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.1381926,2026-11-03T01:28:52.742851Z RE-01_A3_r2_fable,1,claude-sonnet-5-5,100.0,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 4, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 4, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.0626313,2026-11-03T01:28:58.782516Z RE-01_A3_r2_fable,2,claude-sonnet-5-5,100.0,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 4, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 4, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.0613913,2026-11-03T01:29:04.170501Z BANK-01_A3_r2_fable,0,claude-opus-5-5,100.0,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 4, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 4, ""spreadsheet_quality"": 4}, ""acceptable"": true}",0.152056,2026-11-03T01:31:30.064984Z BANK-01_A3_r2_fable,1,claude-sonnet-5-5,97.5,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 4, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 4, ""spreadsheet_quality"": 3}, ""acceptable"": true}",0.070248,2026-11-03T01:31:36.392920Z BANK-01_A3_r2_fable,2,claude-sonnet-5-5,93.75,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 4, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 3, ""spreadsheet_quality"": 3}, ""acceptable"": true}",0.0690859,2026-11-03T01:31:42.473922Z BI-01_A3_r1_fable,0,claude-opus-5-5,72.5,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 3, ""R3_commentary"": 4, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 1, ""R6_professional_conduct"": 1}, ""acceptable"": false}",0.122526,2026-11-03T01:34:18.884923Z BI-01_A3_r1_fable,1,claude-sonnet-5-5,78.75,"{""scores"": {""R1_accuracy"": 4, ""R2_dashboard"": 3, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 2, ""R6_professional_conduct"": 3}, ""acceptable"": true}",0.055753,2026-11-03T01:34:24.822450Z BI-01_A3_r1_fable,2,claude-sonnet-5-5,78.75,"{""scores"": {""R1_accuracy"": 4, ""R2_dashboard"": 3, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 2, ""R6_professional_conduct"": 3}, ""acceptable"": false}",0.053661900000000005,2026-11-03T01:34:29.978794Z BANK-01_A3_r1_fable,0,claude-opus-5-5,100.0,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 4, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 4, ""spreadsheet_quality"": 4}, ""acceptable"": true}",0.1549468,2026-11-03T01:36:47.406398Z BANK-01_A3_r1_fable,1,claude-sonnet-5-5,97.5,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 4, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 4, ""spreadsheet_quality"": 3}, ""acceptable"": true}",0.0696434,2026-11-03T01:36:53.669756Z BANK-01_A3_r1_fable,2,claude-sonnet-5-5,100.0,"{""scores"": {""financial_analysis_accuracy"": 4, ""policy_application"": 4, ""risk_identification"": 4, ""structuring_and_security"": 4, ""memo_professionalism"": 4, ""spreadsheet_quality"": 4}, ""acceptable"": true}",0.0698059,2026-11-03T01:37:01.063950Z PROC-01_A3_r1_fable,0,claude-opus-5-5,96.25,"{""scores"": {""compliance_screening"": 4, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 4, ""workbook_quality"": 3, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 4}, ""acceptable"": true}",0.14191299999999998,2026-11-03T01:32:12.589113Z PROC-01_A3_r1_fable,1,claude-sonnet-5-5,88.75,"{""scores"": {""compliance_screening"": 4, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 3, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 3}, ""acceptable"": true}",0.062074000000000004,2026-11-03T01:32:18.685501Z PROC-01_A3_r1_fable,2,claude-sonnet-5-5,95.0,"{""scores"": {""compliance_screening"": 4, ""normalisation_accuracy"": 4, ""scoring_fidelity"": 3, ""workbook_quality"": 4, ""recommendation_and_conditions"": 4, ""memo_professionalism"": 4}, ""acceptable"": true}",0.06181400000000001,2026-11-03T01:32:24.597439Z RES-01_A3_r2_fable,0,claude-opus-5-5,80.0,"{""scores"": {""cleaning_log"": 4, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 3, ""reproducibility"": 0, ""professional_judgement"": 2}, ""acceptable"": false}",0.2638454,2026-11-03T01:32:45.846712Z RES-01_A3_r2_fable,1,claude-sonnet-5-5,91.25,"{""scores"": {""cleaning_log"": 4, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 4, ""reproducibility"": 2, ""professional_judgement"": 4}, ""acceptable"": true}",0.1199602,2026-11-03T01:32:52.869490Z RES-01_A3_r2_fable,2,claude-sonnet-5-5,93.75,"{""scores"": {""cleaning_log"": 4, ""specification_fidelity"": 4, ""tables_figure"": 3, ""reference_check"": 4, ""report_quality"": 4, ""reproducibility"": 3, ""professional_judgement"": 4}, ""acceptable"": true}",0.11975770000000001,2026-11-03T01:32:59.356906Z HR-01_A3_r2_fable,0,claude-opus-5-5,75.0,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 3, ""workbook_usability"": 4}, ""acceptable"": false}",0.149976,2026-11-03T01:35:41.923388Z HR-01_A3_r2_fable,1,claude-sonnet-5-5,76.25,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 4, ""workbook_usability"": 3}, ""acceptable"": false}",0.07024550000000002,2026-11-03T01:35:47.643480Z HR-01_A3_r2_fable,2,claude-sonnet-5-5,76.25,"{""scores"": {""payroll_accuracy"": 3, ""data_quality_handling"": 4, ""policy_judgement"": 4, ""correspondence"": 0, ""summary_clarity"": 4, ""workbook_usability"": 3}, ""acceptable"": false}",0.0684022,2026-11-03T01:35:53.145210Z FIN-01_A3_r2_fable,0,claude-opus-5-5,82.5,"{""scores"": {""model_integrity"": 3, ""discount_rate"": 3, ""balance_sheet_judgement"": 3, ""memo_quality"": 4, ""independent_judgement"": 3, ""completeness_and_disclosure"": 4}, ""acceptable"": true}",0.143131,2026-11-03T01:35:43.173526Z FIN-01_A3_r2_fable,1,claude-sonnet-5-5,90.0,"{""scores"": {""model_integrity"": 4, ""discount_rate"": 3, ""balance_sheet_judgement"": 3, ""memo_quality"": 4, ""independent_judgement"": 4, ""completeness_and_disclosure"": 3}, ""acceptable"": true}",0.058948,2026-11-03T01:35:49.552943Z FIN-01_A3_r2_fable,2,claude-sonnet-5-5,75.0,"{""scores"": {""model_integrity"": 3, ""discount_rate"": 3, ""balance_sheet_judgement"": 3, ""memo_quality"": 3, ""independent_judgement"": 3, ""completeness_and_disclosure"": 3}, ""acceptable"": true}",0.058035500000000004,2026-11-03T01:35:55.471444Z RE-01_A3_r1_fable,0,claude-opus-5-5,100.0,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 4, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 4, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.1368576,2026-11-03T01:38:41.512419Z RE-01_A3_r1_fable,1,claude-sonnet-5-5,91.25,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 3, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 3, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.0600263,2026-11-03T01:38:46.929190Z RE-01_A3_r1_fable,2,claude-sonnet-5-5,91.25,"{""scores"": {""comparable_selection"": 4, ""adjustment_grid"": 3, ""subject_description"": 4, ""reconciliation_and_value"": 4, ""report_completeness"": 3, ""assumptions_and_anomaly_handling"": 4}, ""acceptable"": true}",0.0598613,2026-11-03T01:38:52.525340Z ACC-01_A3_r2_fable,0,claude-opus-5-5,100.0,"{""scores"": {""reconciliation_mechanics"": 4, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 4, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.152586,2026-11-03T01:40:48.916741Z ACC-01_A3_r2_fable,1,claude-sonnet-5-5,96.25,"{""scores"": {""reconciliation_mechanics"": 4, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 3, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.067573,2026-11-03T01:40:54.551116Z ACC-01_A3_r2_fable,2,claude-sonnet-5-5,96.25,"{""scores"": {""reconciliation_mechanics"": 4, ""discrepancy_detection"": 4, ""correcting_entries"": 4, ""cash_position"": 3, ""report_quality"": 4, ""professional_judgement"": 4}, ""acceptable"": true}",0.06672990000000001,2026-11-03T01:41:00.442231Z ADM-01_A3_r1_fable,0,claude-opus-5-5,56.25,"{""scores"": {""prioritisation"": 3, ""replies"": 0, ""calendar"": 4, ""briefing"": 3, ""filing"": 0, ""risk_handling"": 3}, ""acceptable"": false}",0.122886,2026-11-03T01:44:26.878806Z ADM-01_A3_r1_fable,1,claude-sonnet-5-5,72.5,"{""scores"": {""prioritisation"": 3, ""replies"": 1, ""calendar"": 4, ""briefing"": 4, ""filing"": 1, ""risk_handling"": 4}, ""acceptable"": false}",0.0577655,2026-11-03T01:44:32.982767Z ADM-01_A3_r1_fable,2,claude-sonnet-5-5,72.5,"{""scores"": {""prioritisation"": 3, ""replies"": 1, ""calendar"": 4, ""briefing"": 4, ""filing"": 1, ""risk_handling"": 4}, ""acceptable"": false}",0.0564063,2026-11-03T01:44:40.122866Z BI-01_A3_r2_fable,0,claude-opus-5-5,62.5,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 2, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 1, ""R6_professional_conduct"": 1}, ""acceptable"": false}",0.1085238,2026-11-03T01:45:58.073380Z BI-01_A3_r2_fable,1,claude-sonnet-5-5,68.75,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 3, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 1, ""R6_professional_conduct"": 2}, ""acceptable"": false}",0.0488419,2026-11-03T01:46:04.091187Z BI-01_A3_r2_fable,2,claude-sonnet-5-5,68.75,"{""scores"": {""R1_accuracy"": 3, ""R2_dashboard"": 3, ""R3_commentary"": 3, ""R4_data_quality"": 3, ""R5_methodology_reproducibility"": 1, ""R6_professional_conduct"": 2}, ""acceptable"": false}",0.0491744,2026-11-03T01:46:09.839993Z ADM-01_A3_r2_fable,0,claude-opus-5-5,56.25,"{""scores"": {""prioritisation"": 3, ""replies"": 0, ""calendar"": 4, ""briefing"": 3, ""filing"": 0, ""risk_handling"": 3}, ""acceptable"": false}",0.12089760000000001,2026-11-03T01:44:45.779252Z ADM-01_A3_r2_fable,1,claude-sonnet-5-5,68.75,"{""scores"": {""prioritisation"": 3, ""replies"": 1, ""calendar"": 4, ""briefing"": 4, ""filing"": 1, ""risk_handling"": 3}, ""acceptable"": false}",0.0554988,2026-11-03T01:44:51.439505Z ADM-01_A3_r2_fable,2,claude-sonnet-5-5,73.75,"{""scores"": {""prioritisation"": 4, ""replies"": 1, ""calendar"": 4, ""briefing"": 4, ""filing"": 1, ""risk_handling"": 3}, ""acceptable"": false}",0.0552838,2026-11-03T01:44:56.899662Z LEGAL-01_A3_r2_fable,0,claude-opus-5-5,93.75,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 4, ""open_items"": 4, ""presentation"": 3}, ""acceptable"": true}",0.11906639999999999,2026-11-03T01:42:46.717739Z LEGAL-01_A3_r2_fable,1,claude-sonnet-5-5,91.25,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 3, ""open_items"": 4, ""presentation"": 4}, ""acceptable"": true}",0.053025699999999995,2026-11-03T01:42:52.408841Z LEGAL-01_A3_r2_fable,2,claude-sonnet-5-5,96.25,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 4, ""open_items"": 4, ""presentation"": 4}, ""acceptable"": true}",0.0525932,2026-11-03T01:42:58.715406Z LEGAL-01_A3_r1_fable,0,claude-opus-5-5,93.75,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 4, ""open_items"": 4, ""presentation"": 3}, ""acceptable"": true}",0.1237364,2026-11-03T01:42:47.456351Z LEGAL-01_A3_r1_fable,1,claude-sonnet-5-5,91.25,"{""scores"": {""coverage"": 4, ""calibration"": 3, ""redlines"": 4, ""memo"": 3, ""open_items"": 4, ""presentation"": 4}, ""acceptable"": true}",0.053180700000000004,2026-11-03T01:42:52.965785Z LEGAL-01_A3_r1_fable,2,claude-sonnet-5-5,92.5,"{""scores"": {""coverage"": 4, ""calibration"": 2, ""redlines"": 4, ""memo"": 4, ""open_items"": 4, ""presentation"": 4}, ""acceptable"": true}",0.053233199999999994,2026-11-03T01:42:59.635928Z