Home Model series Claude Fable Claude Fable 5.1 Claude Fable 5.1 · HealthBench Professional · 525 physician-authored conversations · Scores and configurations Claude Fable 5.1 · HealthBench Professional · 525 physician-authored conversations · Scores and configurations Claude Fable 5.1 record for HealthBench Professional · 525 physician-authored conversations. 2 score records for this release, including 2 exact values (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Fable 5.1 · HealthBench Professional scores and configurations Metric and score Configuration and evaluation conditions Sources Raw score 74.2% Reported 74.2% · Unit % Published Unconfirmed
Adaptive Max Settings Claude Fable 5.1;CursorBench 主文引述明确为 max effort;后续 System Card 对 OSWorld/BenchCAD/OfficeQA 对照结果亦标 max effort。 Unknowns 不同 benchmark 的具体执行细节分别见来源章节;部分测试的采样参数或运行数未单独公布。 Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol HealthBench Professional; 525 physician-authored conversations; average over five trials; adaptive max effort. Conditions Production safety classifiers and fallback to Opus 5 on classifier block. View this score in rankings Length-adjusted score 62.1% Reported 62.1% · Unit % Published Unconfirmed
Adaptive Max Settings Claude Fable 5.1;CursorBench 主文引述明确为 max effort;后续 System Card 对 OSWorld/BenchCAD/OfficeQA 对照结果亦标 max effort。 Unknowns 不同 benchmark 的具体执行细节分别见来源章节;部分测试的采样参数或运行数未单独公布。 Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol HealthBench Professional; length-adjusted score; average over five trials; adaptive max effort. Conditions Production safety classifiers and fallback to Opus 5 on classifier block. View this score in rankings
Sources and disclosures 本地留存副本, PDF p.199 Attachment · Claude Fable 5.1 and Claude Mythos 5.1 System Card Benchmark versions and metrics Aliases HealthBench Professional
Raw score · % · Higher is better Length-adjusted score · % · Higher is better Score · % · Higher is better Mean response length · characters · Ranking direction unconfirmed 长度校正分(0–100) · score · Higher is better 未校正分(0–100) · score · Higher is better 相对 GPT-5.4 的长度校正分差 · points · Ranking direction unconfirmed Unadjusted score · % · Higher is better