Global MMLU · 42 languages including English · overall average · 测试定义与成绩

Global MMLU · 42 languages including English · overall average 收录 9 次模型发布的评测披露或成绩。

测试版本与指标

别名 GMMLU、Global MMLU

  • Average accuracy · % · 越高越好
  • Average or worst gap to English · % · 排序方向未确认

各系列最新模型 · 公布成绩

常规展示范围。排名按指标与评测协议分组,已记录的工具、预算及框架分别展示。条件未说明的组保留公布值供查证。

Average accuracy %

禁止工具 / max / 框架未记录 · GMMLU average accuracy across 42 languages; max effort; one trial; no tools or custom system prompt.

Global MMLU · 42 languages including English · overall average · Average accuracy · 禁止工具 / max / 框架未记录 · GMMLU average accuracy across 42 languages; max effort; one trial; no tools or custom system prompt.
模型与配置成绩(%)记录与证据
Claude Fable 5.2Max96%

禁止工具 / max / 框架未记录 · GMMLU; average accuracy over 42 languages; no tools or customized system prompt; single trial.

Global MMLU · 42 languages including English · overall average · Average accuracy · 禁止工具 / max / 框架未记录 · GMMLU; average accuracy over 42 languages; no tools or customized system prompt; single trial.
模型与配置成绩(%)记录与证据
Claude Haiku 5.5Max87.8%

禁止工具 / max / 框架未记录 · GMMLU average accuracy across 42 languages; one trial.

Global MMLU · 42 languages including English · overall average · Average accuracy · 禁止工具 / max / 框架未记录 · GMMLU average accuracy across 42 languages; one trial.
模型与配置成绩(%)记录与证据
Claude Sonnet 5.5Max92.1%

禁止工具 / max / 框架未记录 · GMMLU overall accuracy across 42 languages; adaptive thinking/max effort; one trial; no tools or customized system prompt.

Global MMLU · 42 languages including English · overall average · Average accuracy · 禁止工具 / max / 框架未记录 · GMMLU overall accuracy across 42 languages; adaptive thinking/max effort; one trial; no tools or customized system prompt.
模型与配置成绩(%)记录与证据
Claude Opus 5.5Max94.3%

历史记录 · 9 次发布

  • Claude Fable 5.2本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
  • Claude Haiku 5.5本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
  • Claude Sonnet 5.5本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
  • Claude Opus 5.5本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
  • Claude Opus 5本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
  • Claude Sonnet 5本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
  • Claude Opus 4.8本次发布有 3 条成绩记录,含 3 条精确值(可含历史记录)
  • Claude Opus 4.7本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
  • Claude Sonnet 4.6本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)