PaperBench · 10-paper subset; each paper requires <10GB external data · Benchmark definition and scores
PaperBench · 10-paper subset; each paper requires <10GB external data has benchmark disclosures or scores across 2 model releases.
Benchmark versions and metrics
Aliases PaperBench-10 (<10GB)
- Pass@1 · % · Higher is better
Latest models by series · reported scores
The latest models in each named series have no scores to display in this scope. Recorded historical data appears below.
History · 2 releases
- GPT-5.1 Codex-Max1 score record for this release, including 1 exact value (may include historical records)
- GPT-5.11 score record for this release, including 1 exact value (may include historical records)