# Amazon Nova Pro vs DeepSeek-V3.2-Speciale

> DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 31.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-deepseek-v3-2-speciale
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.9 to 20.0.
- DeepSeek-V3.2-Speciale is cheaper at $0.58 / $1.68 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 128K.
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 31.0 | 39.7 |
| Rank | 281 | 162 |
| Context | 300K | 128K |
| Input $/M | $0.80 | $0.58 |
| Output $/M | $3.20 | $1.68 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- DeepSeek-V3.2-Speciale: 40.4 (#140)

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| WeirdML | — | 46.7% |
| LiveBench Coding | 38.1% | — |
| LMArena Coding | 1270 | — |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- DeepSeek-V3.2-Speciale: —

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- DeepSeek-V3.2-Speciale: 32.9 (#73)

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| SimpleBench | — | 52.6% |
| LiveBench Reasoning | 32.6% | — |
| LMArena Hard Prompts | 1246 | — |
| LiveBench Data Analysis | 48.3% | — |
| Epoch Capabilities Index | 123.8 | — |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 28.5 (#243)
- DeepSeek-V3.2-Speciale: —

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| LMArena Math | 1252 | — |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- DeepSeek-V3.2-Speciale: —

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| LMArena Expert | 1211 | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- DeepSeek-V3.2-Speciale: —

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- DeepSeek-V3.2-Speciale: —

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Non-English | 1234 | — |
| LMArena Chinese | 1244 | — |
| LMArena French | 1271 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Russian | 1240 | — |
| LMArena Spanish | 1182 | — |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- DeepSeek-V3.2-Speciale: —

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
| LMArena Instruction Following | 1235 | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- DeepSeek-V3.2-Speciale: —

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Longer Query | 1255 | — |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- DeepSeek-V3.2-Speciale: 46.0 (#222)

| Benchmark | Amazon Nova Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Text | 1259 | — |
| LMArena Creative Writing | 1212 | — |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 1276 |
| WildBench | 77.7% | — |
| LMArena Multi-Turn | 1246 | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than DeepSeek-V3.2-Speciale?

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 31.0 on the Noometry Index.

### Which is cheaper, Amazon Nova Pro or DeepSeek-V3.2-Speciale?

DeepSeek-V3.2-Speciale is cheaper. It lists at $0.58 per million input tokens and $1.68 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or DeepSeek-V3.2-Speciale better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 128K.

### How many benchmarks do Amazon Nova Pro and DeepSeek-V3.2-Speciale share?

0 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.