FormulaForest

Search everything

Mentions · 7d0
Mentions · 30d1
All mentions1
First seenOct 23, 2026
Last mentioned19d ago

Timeline

1 articles · newest first

PHYRD benchmark tests LLMs on reproducing and extending physics

Across five models, Reproduce accuracy was 49.21%–68.25% and closed-book Discover was 18.60%–74.42%.

arXiv cs.AI / cs.LG / cs.CLOct 23, 13:03 UTC · 19d agoAI research1

Appears with

PHYRDproduct · 1
Qwen-35B-A3Bai model · 1
FrontierScienceproduct · 1
OpenAIorganization · 1

Entities are extracted by the model from each article. First seen Oct 23, 2026, last mentioned 19d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.