SU
Stanford University
Language model · United States ·Jan 2025

s1

Language Open (Restricted)
32B
Parameters
8
Benchmarks

About s1

s1 is an AI model developed by Stanford University, in the language category, released in 2025, made available as an open-weights model with 32B params.

On this page you'll find s1's full specifications, including 8 benchmark results. Review provider pricing and benchmark scores below, or compare s1 head-to-head with other language models.

→ More models by Stanford University → All language models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run s1 locally — what to buy

Share this build ↗

Sized to what s1 actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
AMD Radeon RX 7900 XTX
Consumer GPU · ~$999
~41.3 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
NVIDIA GeForce RTX 4090
Consumer GPU · ~$1,599
~48.9 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5090
Consumer GPU · ~$1,999
~87 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
11–87 tok/s
9 options →
Apple
13.7–36.6 tok/s
17 options →
Datacenter GPU
37.1–120+ tok/s
13 options →

Community

Would you run s1 again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

s1 benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
AIME 2024 math 56.7% s1-1-from-hf-readme
AIME 2024 math 56.7% s1-from-hf-readme
AIME 2025 math 60% s1-1-aime25-i-from-hf-readme
AIME 2025 math 26.7% s1-aime25-i-from-hf-readme
MATH-500 math 95.4% s1-1-from-hf-readme
MATH-500 math 93% s1-from-hf-readme
GPQA Diamond reasoning 63.6% s1-1-from-hf-readme
GPQA Diamond reasoning 59.6% s1-from-hf-readme

More models like s1

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is s1? ▶

s1 is an AI model developed by Stanford University, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created s1? ▶

s1 was developed by Stanford University and released in 2025.

Is s1 open source or proprietary? ▶

s1 ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does s1 cost? ▶

Pricing for s1 depends on the provider. See the providers table on this page for the latest API rates.

How does s1 perform on benchmarks? ▶

s1 is benchmarked across 8 evaluations on GenAIList, including AIME 2024 (56.7%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about s1?