Max effort; no tools or customized system prompts; Opus 4.8 grader; five-trial average; length-adjustment method from the HealthBench Professional paper.
未知项
未另记
工具
禁止工具
推理预算
max
框架
未记录
协议
HealthBench Professional; length-adjusted score.
条件
59.8%; card also reports raw score 73.4%; max effort, no tools/custom system prompt, Opus 4.8 grader, five-trial average.
Max effort; no tools or customized system prompts; Opus 4.8 grader; five-trial average; length-adjustment method from the HealthBench Professional paper.
未知项
未另记
工具
禁止工具
推理预算
max
框架
未记录
协议
HealthBench Professional; raw rubric score.
条件
Max effort; no tools or customized system prompt; Opus 4.8 grader; five-trial average.
HealthBench Professional max effort with safeguards
设置
Adaptive thinking/max effort; safety classifiers enabled and refusal fallback to Opus 5; no tools or customized system prompts; five trials.
未知项
未另记
工具
禁止工具
推理预算
max
框架
未记录
协议
HealthBench Professional; raw score; five trials; no tools or customized system prompt.
条件
Safety classifiers enabled with refusal fallback to Opus 5. Source-wide conditions: Five trials; no tools or customized system prompts; safety classifiers enabled with refusal fallback to Opus 5.
HealthBench Professional max effort with safeguards
设置
Adaptive thinking/max effort; safety classifiers enabled and refusal fallback to Opus 5; no tools or customized system prompts; five trials.
未知项
未另记
工具
禁止工具
推理预算
max
框架
未记录
协议
HealthBench Professional; length-adjusted score; five trials; no tools or customized system prompt.
条件
Length adjustment penalizes verbose responses; safety classifiers enabled with refusal fallback to Opus 5. Source-wide conditions: Five trials; no tools or customized system prompts; safety classifiers enabled with refusal fallback to Opus 5.
Claude Opus · HealthBench Professional · 525 physician-authored conversations · Release history
View scores, configurations, and disclosures for HealthBench Professional · 525 physician-authored conversations across 3 Claude Opus releases, ordered by release date.
Differences are calculated only for unique, active, exact values between direct predecessors when the unit, metric, and explicitly recorded configuration and conditions match.
· 2 score records for this release, including 2 exact values (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
Claude Opus 5 · HealthBench Professional scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Length-adjusted score59.8%Reported 59.8% · Unit %
Published Unconfirmed
HealthBench Professional · max
Settings
Max effort; no tools or customized system prompts; Opus 4.8 grader; five-trial average; length-adjustment method from the HealthBench Professional paper.
Unknowns
none recorded
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
HealthBench Professional; length-adjusted score.
Conditions
59.8%; card also reports raw score 73.4%; max effort, no tools/custom system prompt, Opus 4.8 grader, five-trial average.
Max effort; no tools or customized system prompts; Opus 4.8 grader; five-trial average; length-adjustment method from the HealthBench Professional paper.
Unknowns
none recorded
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
HealthBench Professional; raw rubric score.
Conditions
Max effort; no tools or customized system prompt; Opus 4.8 grader; five-trial average.
· 2 score records for this release, including 2 exact values (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
Claude Opus 5.5 · HealthBench Professional scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Raw score77.1%Reported 77.1% raw rubric score · Unit %
Published Unconfirmed
HealthBench Professional max effort with safeguards
Settings
Adaptive thinking/max effort; safety classifiers enabled and refusal fallback to Opus 5; no tools or customized system prompts; five trials.
Unknowns
none recorded
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
HealthBench Professional; raw score; five trials; no tools or customized system prompt.
Conditions
Safety classifiers enabled with refusal fallback to Opus 5. Source-wide conditions: Five trials; no tools or customized system prompts; safety classifiers enabled with refusal fallback to Opus 5.
Length-adjusted score65.6%Reported 65.6% length-adjusted score · Unit %
Published Unconfirmed
HealthBench Professional max effort with safeguards
Settings
Adaptive thinking/max effort; safety classifiers enabled and refusal fallback to Opus 5; no tools or customized system prompts; five trials.
Unknowns
none recorded
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
HealthBench Professional; length-adjusted score; five trials; no tools or customized system prompt.
Conditions
Length adjustment penalizes verbose responses; safety classifiers enabled with refusal fallback to Opus 5. Source-wide conditions: Five trials; no tools or customized system prompts; safety classifiers enabled with refusal fallback to Opus 5.