DE
DeepSeek
Language model · China ·Sep 2025

DeepSeek-V3.2-Exp

Language Open (Restricted)
671B
Parameters
14
Benchmarks

About DeepSeek-V3.2-Exp

DeepSeek-V3.2-Exp is an AI model developed by DeepSeek, in the language category, released in 2025, made available as an open-weights model with 671B params.

On this page you'll find DeepSeek-V3.2-Exp's full specifications, including 14 benchmark results. Review provider pricing and benchmark scores below, or compare DeepSeek-V3.2-Exp head-to-head with other language models.

Links

Run DeepSeek-V3.2-Exp locally — what it takes

DeepSeek-V3.2-Exp (671B) is too large to run on a single consumer or Apple machine. At Q4 its weights alone are about 376 GB — it needs a multi-GPU / datacenter setup:

  • ≈ 2× AMD Instinct MI325X
  • ≈ 3× NVIDIA B200

Lower quantization (Q3/Q2) or CPU + system-RAM offload (e.g. ktransformers) reduces the requirement at the cost of speed.

Software support

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

Community

Would you run DeepSeek-V3.2-Exp 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.

DeepSeek-V3.2-Exp benchmark scores
Benchmark Category Score Variant
BrowseComp agentic 40.1% from-hf-readme
BrowseComp-Zh agentic 47.9 from-hf-readme
Terminal-Bench 2.0 agentic 37.7% from-hf-readme
Aider Polyglot code 74.5% from-hf-readme
Codeforces Elo code 2,121 from-hf-readme
LiveCodeBench code 74.1% from-hf-readme
SWE-bench Verified code 67.8% from-hf-readme
SWE-Bench Multilingual coding 57.9 from-hf-readme
MMLU-Pro general 85% from-hf-readme
AIME 2025 math 89.3% from-hf-readme
HMMT February 2025 math 83.6% from-hf-readme
GPQA Diamond reasoning 79.9% from-hf-readme
Humanity's Last Exam reasoning 19.8% from-hf-readme
SimpleQA safety 97.1% from-hf-readme

More models like DeepSeek-V3.2-Exp

Frequently asked questions

What is DeepSeek-V3.2-Exp?

DeepSeek-V3.2-Exp is an AI model developed by DeepSeek, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created DeepSeek-V3.2-Exp?

DeepSeek-V3.2-Exp was developed by DeepSeek and released in 2025.

Is DeepSeek-V3.2-Exp open source or proprietary?

DeepSeek-V3.2-Exp 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 DeepSeek-V3.2-Exp cost?

Pricing for DeepSeek-V3.2-Exp depends on the provider. See the providers table on this page for the latest API rates.

How does DeepSeek-V3.2-Exp perform on benchmarks?

DeepSeek-V3.2-Exp is benchmarked across 14 evaluations on GenAIList, including BrowseComp (40.1%). See the full benchmark table below and compare it with other models.

Deepseek V3.2 Exp: CHEAPEST Model Ever That Is Quite POWERFUL! Best Opensource Model?

Know a great video about DeepSeek-V3.2-Exp?