Home Model series Claude Opus Claude Opus 4.8 Claude Opus 4.8 · CharXiv Reasoning · Validation split · Scores and configurations Claude Opus 4.8 · CharXiv Reasoning · Validation split · Scores and configurations Claude Opus 4.8 record for CharXiv Reasoning · Validation split. 2 score records for this release, including 2 exact values (may include historical records). Includes 2 source locations.
Scores and evaluation conditions Claude Opus 4.8 · CharXiv Reasoning scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 80.5% Reported 80.5% · Unit % Published Unconfirmed
视觉基准无工具 Settings Adaptive thinking、max effort、无工具;各图表注明时平均 5 runs,95% CI。 Unknowns none recorded Tools Tools forbidden Reasoning budget max Framework not recorded Protocol CharXiv Reasoning validation split, 1,000 questions; average over 5 runs; new grader. Conditions Adaptive thinking/max effort, no tools. View this score in rankings Accuracy 89.9% Reported 89.9% · Unit % Published Unconfirmed
视觉基准 Python 工具 Settings Adaptive thinking、max effort、Python tools;各图表注明时平均 5 runs,95% CI。 Unknowns none recorded Tools Tools allowed Reasoning budget max Framework not recorded Protocol CharXiv Reasoning validation split, 1,000 questions; average over 5 runs; new grader. Conditions Adaptive thinking/max effort with Python tools. View this score in rankings
Benchmark versions and metrics Aliases CharXiv Reasoning
Accuracy · % · Higher is better