Novelty Bench

1. 2026-10-28
   Novelty BenchPOSTED ONHugging Face

   Novelty Bench is posted on Hugging Face

   当前有效1 条来源Hugging Face
2. 2026-10-28
   GPT-5.1USED INNovelty Bench

   GPT-5.1 is used in Novelty Bench evaluation

   当前有效1 条来源GPT-5.1
3. 2026-10-28
   GPT-5.2USED INNovelty Bench

   GPT-5.2 is used in Novelty Bench evaluation

   当前有效1 条来源GPT-5.2
4. 2026-10-28
   Claude Opus 4.6USED INNovelty Bench

   Claude Opus 4.6 is used in Novelty Bench evaluation

   当前有效1 条来源Claude Opus 4.6
5. 2026-10-28
   Allen Institute for AIPUBLISHESNovelty Bench

   Allen Institute for AI publishes Novelty Bench

   当前有效1 条来源Allen Institute for AI
6. 2026-10-28
   GPT‑5.4USED INNovelty Bench

   GPT-5.4 is used in Novelty Bench evaluation

   当前有效1 条来源GPT‑5.4
7. 2026-10-28
   ForethoughtPROVIDED REVIEW DATA FORNovelty Bench

   ICLR 2026 provided review data for Novelty Bench

   当前有效1 条来源Forethought
8. 2026-10-28
   My obituary for programmingUSED INNovelty Bench

   Claude Sonnet 4.5 is used in Novelty Bench evaluation

   当前有效1 条来源My obituary for programming
9. 2026-10-28
   Claude Opus 4.5USED INNovelty Bench

   Claude Opus 4.5 is used in Novelty Bench evaluation

   当前有效1 条来源Claude Opus 4.5

关系是 Graphiti 从报道中提取的事实陈述，不是原文引述；失效时间表示后来的报道显示这条关系已不成立。