{"source":"CDSBench","benchmarkVersion":"v0.1","url":"https://cdsbench.com/compare?models=claude,gpt","generatedAt":"2026-09-16T11:29:16.163Z","license":"Public benchmark results may be reused with attribution to CDSBench and a link to the source URL. Source documents are not included.","category":null,"models":[{"model":"Claude","version":"Claude Sonnet 5","ranked":true,"overall":91.2223,"accuracy":0.9054,"evidence_support":0.9226,"multi_document_reasoning":0.7273,"uncertainty_handling":0.9392,"hallucinated_evidence_rate":0.0608,"false_high_confidence_rate":0,"questions":296,"category_accuracy":null,"category_n":null,"byCategory":{"CURRENCY":{"n":28,"correct":28,"accuracy":1},"EVIDENCE":{"n":30,"correct":30,"accuracy":1},"MATURITY":{"n":26,"correct":26,"accuracy":1},"SENIORITY":{"n":30,"correct":30,"accuracy":1},"EXTRACTION":{"n":56,"correct":56,"accuracy":1},"UNCERTAINTY":{"n":32,"correct":22,"accuracy":0.6875},"ENTITY_MATCH":{"n":30,"correct":30,"accuracy":1},"CONTRADICTION":{"n":2,"correct":2,"accuracy":1},"RESTRUCTURING":{"n":2,"correct":2,"accuracy":1},"DELIVERABILITY":{"n":30,"correct":25,"accuracy":0.8333333333333334},"TRANSFERABILITY":{"n":30,"correct":17,"accuracy":0.5666666666666667}}},{"model":"GPT","version":"GPT-5","ranked":true,"overall":61.4925,"accuracy":0.8108,"evidence_support":0.212,"multi_document_reasoning":0.7879,"uncertainty_handling":0.3333,"hallucinated_evidence_rate":0.1486,"false_high_confidence_rate":0.1892,"questions":296,"category_accuracy":null,"category_n":null,"byCategory":{"CURRENCY":{"n":28,"correct":28,"accuracy":1},"EVIDENCE":{"n":30,"correct":0,"accuracy":0},"MATURITY":{"n":26,"correct":26,"accuracy":1},"SENIORITY":{"n":30,"correct":30,"accuracy":1},"EXTRACTION":{"n":56,"correct":54,"accuracy":0.9642857142857143},"UNCERTAINTY":{"n":32,"correct":22,"accuracy":0.6875},"ENTITY_MATCH":{"n":30,"correct":28,"accuracy":0.9333333333333333},"CONTRADICTION":{"n":2,"correct":2,"accuracy":1},"RESTRUCTURING":{"n":2,"correct":0,"accuracy":0},"DELIVERABILITY":{"n":30,"correct":22,"accuracy":0.7333333333333333},"TRANSFERABILITY":{"n":30,"correct":28,"accuracy":0.9333333333333333}}}]}