Home Model series GPT unsuffixed models GPT-5.1 GPT-5.1 · PaperBench · 10-paper subset; each paper requires <10GB external data · Scores and configurations GPT-5.1 · PaperBench · 10-paper subset; each paper requires <10GB external data · Scores and configurations GPT-5.1 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.
Scores and evaluation conditions GPT-5.1 · PaperBench scores and configurations Metric and score Configuration and evaluation conditions Sources Pass@1 34% Reported 34% · Unit % Published Unconfirmed
Codex-Max system-card later comparison Settings GPT-5.1 comparison bars in the GPT-5.1-Codex-Max System Card; per-model effort not independently identified. Unknowns 比较图没有逐模型明确所有采样与effort设置;不根据对照模型或token预算推定档位。 Tools Tool access not recorded Reasoning budget Extra High Framework not recorded Protocol PaperBench 10-paper subset; each requires <10GB external files; pass@1; no browsing. The section reports Extra High reasoning effort. Conditions 原图明示百分比;未从柱高估数。GPT-5.1对照值属于后续来源。卡片当前修订时点未确认,publishedAt保持null;不混入内部PR/Proof Q&A或风险子任务。 View this score in rankings
Benchmark versions and metrics Aliases PaperBench-10 (<10GB)
Pass@1 · % · Higher is better