GPT-6 Luna · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations) · 附件证据(ev-gpt6-luna-hb)
GPT-6 Luna 的 HealthBench · 48,000+ rubric items across 5,000 multi-turn conversations 官方出处。见《Addendum to GPT-6 Astra System Card: GPT-6.1 Sol (PDF)》PDF p.11 / Table 7 / HealthBench row / GPT-6 Luna column。证据 ev-gpt6-luna-hb。
原文与定位
GPT-6 Luna · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-6 Luna, system-card comparison configuration unspecified配置,长度校正分(0–100) 54.5 score(具体成绩公布时间未确认)。见《Addendum to GPT-6 Astra System Card: GPT-6.1 Sol (PDF)》PDF p.11 / Table 7 / HealthBench row / GPT-6 Luna column。 查看成绩条件
GPT-6 Luna · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-6 Luna, system-card comparison configuration unspecified配置,未校正分(0–100) 50 score(具体成绩公布时间未确认)。见《Addendum to GPT-6 Astra System Card: GPT-6.1 Sol (PDF)》PDF p.11 / Table 7 / HealthBench row / GPT-6 Luna column。 查看成绩条件
GPT-6 Luna · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-6 Luna, system-card comparison configuration unspecified配置,Mean response length 1255 characters(具体成绩公布时间未确认)。见《Addendum to GPT-6 Astra System Card: GPT-6.1 Sol (PDF)》PDF p.11 / Table 7 / HealthBench row / GPT-6 Luna column。 查看成绩条件
GPT-6 Luna: 54.5 (50.0, 1255).
- 官方材料
- Addendum to GPT-6 Astra System Card: GPT-6.1 Sol (PDF) · PDF 第 11 页
- 定位
- 附件 · PDF p.11 / Table 7 / HealthBench row / GPT-6 Luna column
- 材料版本
- 47-page PDF; full text extracted, Table 7 read for HealthBench values, remaining sections not fully reviewed.
- 版本公布
- 未确认
- 披露时间
- 未确认 · 首发/后补未确认
- 采集时间
- 历史依据
- 暂无可靠历史版本依据
引用文本
GPT-6 Luna · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-6 Luna, system-card comparison configuration unspecified配置,长度校正分(0–100) 54.5 score(具体成绩公布时间未确认);GPT-6 Luna · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-6 Luna, system-card comparison configuration unspecified配置,未校正分(0–100) 50 score(具体成绩公布时间未确认);GPT-6 Luna · HealthBench(48,000+ rubric items across 5,000 multi-turn conversations),GPT-6 Luna, system-card comparison configuration unspecified配置,Mean response length 1255 characters(具体成绩公布时间未确认)。官方出处 Addendum to GPT-6 Astra System Card: GPT-6.1 Sol (PDF)(附件,47-page PDF; full text extracted, Table 7 read for HealthBench values, remaining sections not fully reviewed.)PDF p.11 / Table 7 / HealthBench row / GPT-6 Luna column,https://deploymentsafety.openai.com/gpt-6-1-sol/gpt-6-1-sol.pdf#page=11。Benchlog https://benchlog.lekshome.cc/evidence/gpt-6-luna/ev-gpt6-luna-hb/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| 长度校正分(0–100)54.5 score原文 54.5 · 单位 score 公布 未确认 | GPT-6 Luna, system-card comparison configuration unspecified
| 直接支持该成绩 在排名中查看此成绩 |
| 未校正分(0–100)50 score原文 50.0 · 单位 score 公布 未确认 | GPT-6 Luna, system-card comparison configuration unspecified
| 直接支持该成绩 在排名中查看此成绩 |
| Mean response length1255 characters原文 1255 · 单位 characters 公布 未确认 | GPT-6 Luna, system-card comparison configuration unspecified
| 直接支持该成绩 在排名中查看此成绩 |