DeepSeek, open weights
DeepSeek-V3.2-Speciale
DeepSeek-V3.2-Speciale by DeepSeek ranks 162nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 39.7. Its strongest category is reasoning, where it ranks 73rd. API pricing starts at $0.58 per million input tokens and $1.68 per million output tokens, with a 128K-token context window.
Last verified
Specifications
- Noometry rank
- #162 of 354
- Index score
- 39.7
- Evidence
- Reported 3 results
- Provider
DeepSeek- Released
- December 1, 2025
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 128K
- Max output
- 128K
- Input price
- $0.58 / M
- Output price
- $1.68 / M
- Blended price
- $0.85 / M
- Output speed
- Not measured
- Value
- #102 of 219
- Knowledge cutoff
- July 2024
- Input
- text
Category scores
Each category score combines every public result we have in that category.
- Coding 40.4
- Reasoning 32.9
- Writing & Preference 46.0
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 40.4 | #140 | 1 |
| Reasoning | 32.9 | #73 | 1 |
| Writing & Preference | 46.0 | #222 | 1 |
Strengths and weaknesses
Categories where DeepSeek-V3.2-Speciale places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 32.9 | +9.3 | #73 of 350, top 21% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Writing & Preference | 46.0 | −7.8 | #222 of 312, top 72% |
Closest competitors
The models ranked just above and below DeepSeek-V3.2-Speciale. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| GLM-4.5V | #158 | 39.8 | $0.90 | 34 | Compare |
| QwQ-32B | #159 | 39.8 | — | — | Compare |
| Step 1o Turbo 202506 | #160 | 39.7 | — | — | Compare |
| Nova 2 Lite | #161 | 39.7 | $0.85 | — | Compare |
| Hunyuan Turbo 0110 | #163 | 39.6 | — | — | Compare |
| Claude 3.7 Sonnet | #164 | 39.5 | — | — | Compare |
| Claude Haiku 4.5 | #165 | 39.5 | $2 | — | Compare |
| DeepSeek-V3 | #166 | 39.5 | $0.41 | 73 | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| WeirdML | 46.7% | #55 of 119, top 47% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| SimpleBench | 52.6% | #39 of 77, top 51% | Epoch AI |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| EQ-Bench Creative Writing | 1276 | #80 of 115, top 70% | EQ-Bench |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| azure | $0.58 | $1.68 | — | 2026-10-10 |
Compare DeepSeek-V3.2-Speciale
- DeepSeek-V3.2-Speciale vs Nova 2 Lite
- DeepSeek-V3.2-Speciale vs Hunyuan Turbo 0110
- DeepSeek-V3.2-Speciale vs Step 1o Turbo 202506
- DeepSeek-V3.2-Speciale vs Claude 3.7 Sonnet
- DeepSeek-V3.2-Speciale vs QwQ-32B
- DeepSeek-V3.2-Speciale vs Claude Haiku 4.5
- DeepSeek-V3.2-Speciale vs GPT-6 Astra
- DeepSeek-V3.2-Speciale vs Claude Fable 5.1
- DeepSeek-V3.2-Speciale vs Gemini 3.8 Flash
- DeepSeek-V3.2-Speciale vs Kimi K3
- DeepSeek-V3.2-Speciale vs Grok 4.6
- DeepSeek-V3.2-Speciale vs Qwen3.8 Max
- DeepSeek-V3.2-Speciale vs GLM-5.3
- DeepSeek-V3.2-Speciale vs Muse Spark 1.3
Other DeepSeek models
- DeepSeek V4 Pro54.3
- DeepSeek V4 Flash53.6
- DeepSeek V4.1 Flash52.8
- DeepSeek-V3.2-Exp44.3
- DeepSeek-V3.1-Terminus43.1
- DeepSeek-V3.142.8
- DeepSeek-R142.3
- DeepSeek-V339.5
Frequently asked questions
How good is DeepSeek-V3.2-Speciale?
DeepSeek-V3.2-Speciale by DeepSeek ranks 162nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 39.7. Its strongest category is reasoning, where it ranks 73rd. API pricing starts at $0.58 per million input tokens and $1.68 per million output tokens, with a 128K-token context window.
How much does DeepSeek-V3.2-Speciale cost?
DeepSeek-V3.2-Speciale costs $0.58 per million input tokens and $1.68 per million output tokens on azure.
What is DeepSeek-V3.2-Speciale's context window?
DeepSeek-V3.2-Speciale accepts up to 128K tokens of input and can write up to 128K tokens in one response.
Is DeepSeek-V3.2-Speciale open source?
Yes. DeepSeek-V3.2-Speciale's weights are downloadable; check the license for commercial terms.
What are DeepSeek-V3.2-Speciale's strengths and weaknesses?
Relative to other ranked models, DeepSeek-V3.2-Speciale places best in reasoning and lowest in writing & preference.
What is DeepSeek-V3.2-Speciale best at?
Its best category is reasoning, where it ranks 73rd on Noometry.