---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/internlm/Intern-S2-Preview/blob/main/LICENSE
base_model: internlm/Intern-S2-Preview
pipeline_tag: image-text-to-text
---

# Intern-S2-Preview-OPD

**Intern-S2-Preview-OPD** is a post-trained version of
[Intern-S2-Preview](https://huggingface.co/internlm/Intern-S2-Preview), an efficient 35B scientific multimodal foundation model.

The model is post-trained using the method introduced in
[SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation of Long-Context Reasoning](PAPER_LINK_PLACEHOLDER).
This post-training process substantially improves the model's reasoning performance, particularly on challenging proof and mathematical reasoning benchmarks.

## Evaluation Results

| Model | ProofBench | AnswerBench | AIME25 | AMOBench |
|---|---:|---:|---:|---:|
| Intern-S2-Preview | 21.70 | 76.03 | 88.33 | 58.00 |
| **Intern-S2-Preview-OPD** | **44.50 (+22.80)** | **80.10 (+4.07)** | **95.00 (+6.67)** | **59.50 (+1.50)** |
| [SU-01 (Teacher Model)](https://huggingface.co/Simplified-Reasoning/SU-01) | 45.00 | 77.50 | 94.60 | 61.75 |

The values in parentheses indicate absolute improvements over the base model.

## Usage

Intern-S2-Preview-OPD uses the same model architecture and inference interface as Intern-S2-Preview. Please refer to the
[Intern-S2-Preview model card](https://huggingface.co/internlm/Intern-S2-Preview)
for deployment instructions and recommended inference settings.

## License

This model is released under the
[Apache License 2.0](https://huggingface.co/internlm/Intern-S2-Preview/blob/main/LICENSE).