# simplescaling/s1

s1: Simple test-time scaling

Repository: https://github.com/simplescaling/s1
Canonical: https://ross.abutalabs.com/products/s1
Homepage: https://arxiv.org/abs/2501.19393
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-06-25T18:59:18+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 28, release rhythm 35, longevity 41
- inputs: {"age_days": 579, "days_push": 434, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6668, forks 757 (observed 2026-08-28T04:09:47.515238+00:00)

## What it is
s1 is an open-source research project implementing simple test-time scaling for large language models, including the s1K dataset of 1,000 curated questions with reasoning traces, training scripts, and the budget forcing technique. It fine-tunes Qwen2.5-32B-Instruct into s1-32B, a reasoning model that matches or exceeds o1-preview on competition math via controlled test-time compute.

## Use cases
- replicate o1-style reasoning with open models
- fine-tune a model on 1,000 reasoning examples
- control how long a model thinks with budget forcing
- run test-time scaling inference with vLLM
- evaluate reasoning models on math benchmarks like AIME and MATH
- study test-time compute scaling for LLMs

## When to choose
- you want an open, reproducible recipe for o1-like reasoning
- you need budget forcing to extend or terminate model thinking at inference
- you want a small high-quality SFT dataset for reasoning
- you have GPU resources to run or fine-tune a 32B model

## When to avoid
- you need a production-ready serving system rather than research code
- you lack GPUs for 32B model inference or training
- you need a general-purpose chat model rather than a reasoning-focused one
- you want a maintained product with support guarantees

## Facets
- artifact type: library
- maturity: active
- function: llm-training, llm-inference, machine-learning, benchmarking
- domain: large-language-models, machine-learning, artificial-intelligence
- platform: python
- tags: test-time-scaling, budget-forcing, reasoning, fine-tuning, sft, qwen, vllm, research-code, open-weights, research, gpu, linux

## Member repositories
- simplescaling/s1 (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:47.515238+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:43:02.006518+00:00, confidence not recorded.
  - readme: https://github.com/simplescaling/s1 (fetched 2026-08-28T04:09:47.515238+00:00, sha 7402249d7081)
  - homepage: https://arxiv.org/abs/2501.19393 (fetched 2026-08-29T08:39:14.816607+00:00, sha 4d70d0d81f47)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:39:14.825804+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:39:14.829236+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:39:14.831092+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:39:14.827629+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.