Home Model series Claude Fable Claude Fable 5.2 Claude Fable 5.2 · Harvey LAB-AA · Artificial Analysis v1.1; 120-task held-out set; hallucination-gated and ungated all-pass rates · Scores and configurations Claude Fable 5.2 · Harvey LAB-AA · Artificial Analysis v1.1; 120-task held-out set; hallucination-gated and ungated all-pass rates · Scores and configurations Claude Fable 5.2 record for Harvey LAB-AA · Artificial Analysis v1.1; 120-task held-out set; hallucination-gated and ungated all-pass rates. 2 score records for this release, including 2 exact values (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Fable 5.2 · Harvey LAB-AA scores and configurations Metric and score Configuration and evaluation conditions Sources Hallucination-gated all-pass rate 7.2% Reported 7.2% · Unit % Published Unconfirmed
Adaptive Max Settings Claude Fable 5.2;adaptive thinking always on;Max effort;默认 temperature/top_p;Card 通用表说明通常五次运行平均,个别测试另行注明。 Unknowns System Card pp.1-264 文字已完整核读;各benchmark章节未明确披露的运行参数仍未知。 Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol Harvey LAB-AA v1.1 held-out 120-task set; Artificial Analysis evaluation; max effort; average across three judge models. Conditions Task passes only if every criterion is met and no material hallucination appears in the deliverable. View this score in rankings All-pass rate before hallucination gate 10.8% Reported 10.8% · Unit % Published Unconfirmed
Adaptive Max Settings Claude Fable 5.2;adaptive thinking always on;Max effort;默认 temperature/top_p;Card 通用表说明通常五次运行平均,个别测试另行注明。 Unknowns System Card pp.1-264 文字已完整核读;各benchmark章节未明确披露的运行参数仍未知。 Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol Harvey LAB-AA v1.1 held-out 120-task set; Artificial Analysis evaluation; max effort; average across three judge models. Conditions All-pass before the hallucination gate; version 1.1 results are not comparable with previous versions. View this score in rankings
Benchmark versions and metrics Aliases Harvey LAB-AA v1.1
Hallucination-gated all-pass rate · % · Higher is better All-pass rate before hallucination gate · % · Higher is better