Intern-S2-397B

Name: Intern-S2-397B
Author: Shanghai Artificial Intelligence Laboratory

Reasoning modelTool useInternLM

Intern-S2-397B

Also known as: Intern S2 397B

Release date: 2026-09-09Updated: 2026-09-14Views: 34

Live demo GitHub Hugging Face Compare

Parameters

397B

Context length

256K

Multilingual

Supported

Reasoning ability

3/5

Intern-S2-397B is an AI model published by Shanghai Artificial Intelligence Laboratory, released on 2026-09-09, for Reasoning model, with 397B parameters, and 256K context length, with a 89.77 score on MMLU Pro.

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

Intern-S2-397B

Model basics

Reasoning traces

Supported

Thinking modes

Thinking Mode (Default)Standard Mode

Context length

256K tokens

Max output length

32K tokens

Model type

Reasoning model

Modality (in / out)

Text, Image → Text

Release date

2026-09-09

Model file size

No data

MoE architecture

Yes

Total params / Active params

397B / 17B

Knowledge cutoff

No data

Intern-S2-397B

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-S2-397B

Live demo

chat.intern-ai.org.cn

Intern-S2-397B

Official resources

Paper

DataLearnerAI blog

N/A

Intern-S2-397B

API details

API speed

3/5

No public API pricing yet.

Intern-S2-397B

Benchmark Results

Intern-S2-397B currently shows benchmark results led by MMLU Pro (4 / 176, score 89.77), MMMU-Pro (28 / 227, score 81.68), SWE-bench Multilingual (4 / 30, score 84). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.