---

This update maintains the model's original capabilities while addressing issues reported by users, including:

• Language consistency: Reducing instances of mixed Chinese-English text and occasional abnormal characters;
• Agent capabilities: Further optimizing the performance of the Code Agent and Search Agent.

Benchmark	DeepSeek-V3.1	DeepSeek-V3.1-Terminus
Reasoning Mode w/o Tool Use
MMLU-Pro	84.8	85.0
GPQA-Diamond	80.1	80.7
Humanity's Last Exam	15.9	21.7
LiveCodeBench	74.8	74.9
Codeforces	2091	2046
Aider-Polyglot	76.3	76.1
Agentic Tool Use
BrowseComp	30.0	38.5
BrowseComp-zh	49.2	45.0
SimpleQA	93.4	96.8
SWE Verified	66.0	68.4
SWE-bench Multilingual	54.5	57.8
Terminal-bench	31.3	36.7

The template and tool-set of search agent have been updated, which is shown in assets/search_tool_trajectory.html.

The model structure of DeepSeek-V3.1-Terminus is the same as DeepSeek-V3. Please visit DeepSeek-V3 repo for more information about running this model locally.

For the model's chat template other than search agent, please refer to the DeepSeek-V3.1 repo.

Here we also provide an updated inference demo code in the inference folder to help the community get started with running our model and understand the details of model architecture.

NOTE: In the current model checkpoint, the parameters of self_attn.o_proj do not conform to the UE8M0 FP8 scale data format. This is a known issue and will be corrected in future model releases.

This repository and the model weights are licensed under the MIT License.

@misc{deepseekai2024deepseekv3technicalreport,
      title={DeepSeek-V3 Technical Report}, 
      author={DeepSeek-AI},
      year={2024},
      eprint={2412.19437},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.19437}, 
}

If you have any questions, please raise an issue or contact us at service@deepseek.com.