Intern-S1

Name: Intern-S1
Author: Shanghai Artificial Intelligence Laboratory

Multimodal model

Intern-S1

Release date: 2025-07-27Updated: 2025-07-27Views: 937

Live demo GitHub Hugging Face Compare

Parameters

241B

Context length

128K

Multilingual

Supported

Reasoning ability

3/5

Intern-S1 is an AI model published by Shanghai Artificial Intelligence Laboratory, released on 2025-07-27, for Multimodal model, with 241B parameters, and 128K context length, requiring about 481.6 GB storage, with a 86.00 score on AIME2025.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Intern-S1

Model basics

Reasoning traces

Supported

Thinking modes

Standard Mode (Default)Thinking Mode

Context length

128K tokens

Max output length

16K tokens

Model type

Multimodal model

Modality (in / out)

Text, Image → Text

Release date

2025-07-27

Model file size

481.6 GB

MoE architecture

Yes

Total params / Active params

241B / 32B

Knowledge cutoff

No data

Intern-S1

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- Commercial use permitted

GitHub repo

github.com/InternLM/Intern-S1

Hugging Face

huggingface.co/internlm/Intern-S1

Live demo

chat.intern-ai.org.cn

Intern-S1

Official resources

Paper

N/A

DataLearnerAI blog

N/A

Intern-S1

API details

API speed

3/5

No public API pricing yet.

Intern-S1

Benchmark Results

Intern-S1 currently shows benchmark results led by MMLU Pro (46 / 176, score 83.50), MMMU (25 / 74, score 77.70), AIME2025 (74 / 215, score 86). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.