Scaling LLM Test-Time Compute Optimally Can Be More Effective than Scaling Model Parameters

1 Introduction

1. What question does Snell et al.’s study of test-time compute ask?
   If an LLM may use a fixed but substantial amount of compute at inference time on a hard prompt, how much can it improve, and how does spending that compute compare with spending it on a bigger pretrained model?
   • Snell et al., 2025, Scaling LLM Test-Time Compute Optimally Can Be More Effective than Scaling Model Parameters (The Thirteenth International Conference on Learning Representations (ICLR 2025)), §1
2. What were the headline results on scaling test-time compute?
   Choosing the test-time strategy per prompt according to its difficulty (“compute-optimal” scaling) matched best-of-N with about 4× less compute; and in FLOPs-matched comparisons, a small model with extra test-time compute beat a 14× larger model on problems where the small model had non-trivial success, but not on the hardest ones.
   • Snell et al., 2025, Scaling LLM Test-Time Compute Optimally Can Be More Effective than Scaling Model Parameters (The Thirteenth International Conference on Learning Representations (ICLR 2025)), §1