Versions

1 version · Metric: Average replication score

Versions of PaperBench
VersionReleasedModelsResults
PaperBench Code-DevLatestApril 2, 202511

Recently reported results: PaperBench Code-Dev

Latest version: PaperBench Code-Dev

Recently reported results for PaperBench Code-Dev
ModelScoreSource
Qwen3.8-Max93.0%qwen.ai for Qwen3.8-Max on PaperBench Code-Dev (opens in a new tab)Average replication scoreReported Launch postQwen TeamSelf-reportedRecord for Qwen3.8-Max on PaperBench Code-Dev