SSRNOther
Stanfords s1 vs. DeepSeek-R1
The s1 model, trained on a compact dataset, is cost-efficient and accurate in complex reasoning tasks, with a mechanism that allows controllable test-time scaling.
Featured in No. 85 on 19 Feb 2025 · 10 days after release
- Released
- 9 Feb 2025
- First featured
- No. 85 · 19 Feb 2025
- Published in
- Not yet, as far as Semantic Scholar knows
- Shares when featured
- 286
- Identifier
- SSRN 5130864
Citations and venue from Semantic Scholar (ODC-BY), refreshed weekly. Summary: Quant Letter (CC BY 4.0).