GPT-5.1 Codex-Max · PaperBench · 10-paper subset; each paper requires <10GB external data · Scores and configurations
GPT-5.1 Codex-Max record for PaperBench · 10-paper subset; each paper requires <10GB external data. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.