Unless otherwise noted: adaptive thinking at max effort, default temperature/top_p, five-trial average; context window is evaluation-dependent and no more than 1M tokens.
未知项
每个 benchmark 的具体 context window 未逐项列明。
工具
禁止工具
推理预算
max
框架
未记录
协议
GMMLU; average accuracy over 42 languages; no tools or customized system prompt; single trial.
条件
Max effort; safety classifiers enabled; 0.1% blocked or unanswered items were excluded rather than marked incorrect.
Claude Haiku 5.5 · Global MMLU · 42 languages including English · overall average · Scores and configurations
Claude Haiku 5.5 record for Global MMLU · 42 languages including English · overall average. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Claude Haiku 5.5 · Global MMLU scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Average accuracy87.8%Reported 87.8% · Unit %
Published Unconfirmed
System Card 标准 max effort
Settings
Unless otherwise noted: adaptive thinking at max effort, default temperature/top_p, five-trial average; context window is evaluation-dependent and no more than 1M tokens.
Unknowns
每个 benchmark 的具体 context window 未逐项列明。
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
GMMLU; average accuracy over 42 languages; no tools or customized system prompt; single trial.
Conditions
Max effort; safety classifiers enabled; 0.1% blocked or unanswered items were excluded rather than marked incorrect.