Home Model series Claude Opus Claude Opus 4.8 Claude Opus 4.8 · GPQA Diamond · 198-question Diamond subset · Scores and configurations Claude Opus 4.8 · GPQA Diamond · 198-question Diamond subset · Scores and configurations Claude Opus 4.8 record for GPQA Diamond · 198-question Diamond subset. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Opus 4.8 · GPQA Diamond scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 93.6% Reported 93.6% · Unit % Published Unconfirmed
System Card 默认配置 Settings 除章节另有说明外,adaptive thinking at max effort,默认 temperature/top_p,平均 5 trials;评测上下文依任务而定且不超过 1M tokens。 Unknowns none recorded Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol GPQA Diamond, 198-question subset; average over 25 trials. Conditions System Card reports the Diamond subset and trial count. View this score in rankings
Sources and disclosures §8.6, PDF p.198 Attachment · Claude Opus 4.8 System Card Benchmark versions and metrics Aliases GPQA Diamond、GPQA (diamond)
Accuracy · % · Higher is better