禁止工具 / medium / 框架未记录 · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · 禁止工具 / medium / 框架未记录 · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
禁止工具 / high / 框架未记录 · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · 禁止工具 / high / 框架未记录 · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
禁止工具 / max / 框架未记录 · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · 禁止工具 / max / 框架未记录 · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
禁止工具 / max / 框架未记录 · HealthBench; length-adjusted score; five trials; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · 禁止工具 / max / 框架未记录 · HealthBench; length-adjusted score; five trials; no tools or customized system prompt.
禁止工具 / max / 框架未记录 · HealthBench; raw score; five trials; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Raw score · 禁止工具 / max / 框架未记录 · HealthBench; raw score; five trials; no tools or customized system prompt.
Regular display scope. Rankings are grouped by metric and evaluation protocol. Recorded tool access, budgets, and frameworks are shown separately. Scores remain available for reference when conditions are unspecified.
Length-adjusted score %
Tool access not recorded / max / Framework not recorded · HealthBench length-adjusted score; Artificial Analysis; GPT-4.1 grader; max effort.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tool access not recorded / max / Framework not recorded · HealthBench length-adjusted score; Artificial Analysis; GPT-4.1 grader; max effort.
Tools forbidden / low / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tools forbidden / low / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
Tools forbidden / medium / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tools forbidden / medium / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
Tools forbidden / high / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tools forbidden / high / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
Tools forbidden / xhigh / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tools forbidden / xhigh / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
Tools forbidden / max / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tools forbidden / max / Framework not recorded · HealthBench length-adjusted score; Claude Opus 4.8 grader; no tools or customized system prompt.
Tool access not recorded / medium / Framework not recorded · HealthBench length-adjusted score.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tool access not recorded / medium / Framework not recorded · HealthBench length-adjusted score.
Tool access not recorded / high / Framework not recorded · HealthBench length-adjusted score.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tool access not recorded / high / Framework not recorded · HealthBench length-adjusted score.
Tools forbidden / max / Framework not recorded · HealthBench; length-adjusted score; five trials; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Length-adjusted score · Tools forbidden / max / Framework not recorded · HealthBench; length-adjusted score; five trials; no tools or customized system prompt.
Tool access not recorded / max / Framework not recorded · HealthBench; Artificial Analysis; GPT-4.1 grader; max effort.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Raw score · Tool access not recorded / max / Framework not recorded · HealthBench; Artificial Analysis; GPT-4.1 grader; max effort.
Tool access not recorded / max / Framework not recorded · HealthBench, max effort.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Raw score · Tool access not recorded / max / Framework not recorded · HealthBench, max effort.
Tools forbidden / max / Framework not recorded · HealthBench; raw score; five trials; no tools or customized system prompt.
HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations · Raw score · Tools forbidden / max / Framework not recorded · HealthBench; raw score; five trials; no tools or customized system prompt.