Nova Pro 1.0 vs DeepSeek V3 0324
DeepSeek V3 0324 leads Nova Pro 1.0 on the Artificial Analysis Intelligence Index, 9.7 to 7.0, and DeepSeek V3 0324 costs 3.0x less per output token ($1.07 vs $3.20 per million). Updated October 21, 2026; 11 benchmarks have a result for both.
Nova Pro 1.0 or DeepSeek V3 0324: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Nova Pro 1.0 for a larger context window (300K against 164K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
- Shared results
- 11
- Nova Pro 1.0 only
- 31
- DeepSeek V3 0324 only
- 24
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
DeepSeek V3 0324
DeepSeek V3 0324 leads, 9.7 against 7.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V3 0324 has a AA Agentic Index result, 0.8.
Directional only
Reasoning
GPQA Diamond
No call
Only DeepSeek V3 0324 has a GPQA Diamond result, 61.6%.
Directional only
Math
AIME
No call
Only DeepSeek V3 0324 has a AIME result, 52.2%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V3 0324 has a MMLU Pro result, 79.5%.
Directional only
Web design
Design Arena: websites
No call
Only Nova Pro 1.0 has a Design Arena: websites result, 796.
Directional only
Long documents
Listed context window
Nova Pro 1.0
Nova Pro 1.0 takes 300K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3 0324
Nova Pro 1.0 $0.0024, DeepSeek V3 0324 $0.0008 per turn.
List prices
At a glance
- Coding index
- Nova Pro 1.0 not benchmarked, DeepSeek V3 0324 not benchmarked.
- Widest category
- Math, 34.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- AA Math Index: Nova Pro 1.0 7.0 against DeepSeek V3 0324 41.0, 34.0 points apart on a 0 to 100 scale.
- Output price
- Nova Pro 1.0 $3.20 against DeepSeek V3 0324 $1.07 per million output tokens, 3.0x apart.
- Context window
- Nova Pro 1.0 takes 300K tokens, DeepSeek V3 0324 164K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Nova Pro 1.0 | Bars | DeepSeek V3 0324 | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 1 | ||
| General | 0 | 2 | ||
| All shared boards | 0 | 11 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 42.0% | Only DeepSeek V3 0324 measured |
| AA Coding Index | Not measured | 21.2 | Only DeepSeek V3 0324 measured |
| LiveCodeBench (Vals AI) | Not measured | 65.5% | Only DeepSeek V3 0324 measured |
| LiveCodeBench (Artificial Analysis run) | 23.3% | 40.5% | DeepSeek V3 0324 |
| SciCode | Not measured | 39.0% | Only DeepSeek V3 0324 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 6.1% | 15.2% | DeepSeek V3 0324 |
| WeirdML | Not measured | 36.1% | Only DeepSeek V3 0324 measured |
| LMArena Text: coding | 1270 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: software and IT | 1271 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.0 | 9.7 | DeepSeek V3 0324 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 0.8 | Only DeepSeek V3 0324 measured |
| τ²-Bench Telecom | 14.0% | 47.1% | DeepSeek V3 0324 |
| METR time horizons | Not measured | 49.6% | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 61.6% | Only DeepSeek V3 0324 measured |
| GPQA Diamond (Artificial Analysis run) | 49.9% | 65.5% | DeepSeek V3 0324 |
| Humanity's Last Exam (Artificial Analysis run) | 3.2% | 4.7% | DeepSeek V3 0324 |
| GPQA Diamond (Epoch AI run) | Not measured | 67.6% | Only DeepSeek V3 0324 measured |
| SimpleBench | Not measured | 27.2% | Only DeepSeek V3 0324 measured |
| LMArena Text: hard prompts | 1246 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: expert | 1211 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: hard prompts in English | 1259 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 14 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| AIME | Not measured | 52.2% | Only DeepSeek V3 0324 measured |
| MATH 500 (Vals AI) | Not measured | 88.6% | Only DeepSeek V3 0324 measured |
| MGSM (Vals AI) | Not measured | 91.7% | Only DeepSeek V3 0324 measured |
| AA Math Index | 7.0 | 41.0 | DeepSeek V3 0324 |
| AIME 2025 (Artificial Analysis run) | 7.0% | 41.0% | DeepSeek V3 0324 |
| OTIS Mock AIME | Not measured | 37.8% | Only DeepSeek V3 0324 measured |
| MATH level 5 | Not measured | 75.5% | Only DeepSeek V3 0324 measured |
| LMArena Text: math | 1252 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: mathematical work | 1261 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 79.5% | Only DeepSeek V3 0324 measured |
| LegalBench (Vals AI) | Not measured | 77.7% | Only DeepSeek V3 0324 measured |
| CorpFin (Vals AI) | Not measured | 54.7% | Only DeepSeek V3 0324 measured |
| TaxEval (Vals AI) | Not measured | 71.1% | Only DeepSeek V3 0324 measured |
| MedQA (Vals AI) | Not measured | 82.0% | Only DeepSeek V3 0324 measured |
| MMLU Pro (Artificial Analysis run) | 69.1% | 81.9% | DeepSeek V3 0324 |
| MMLU | 82.0% | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: science | 1255 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: medicine and healthcare | 1260 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: legal and government | 1281 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: business and finance | 1229 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| Design Arena: websites | 796 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| IFBench | 38.1% | 41.0% | DeepSeek V3 0324 |
| Long context reasoning (AA-LCR) | 21.0% | 40.7% | DeepSeek V3 0324 |
| DTBench | Not measured | 64.8% | Only DeepSeek V3 0324 measured |
| LMCA | Not measured | 15.5% | Only DeepSeek V3 0324 measured |
| Fiction.LiveBench | Not measured | 50.0% | Only DeepSeek V3 0324 measured |
| Creative writing (Lech Mazur) | Not measured | 77.0% | Only DeepSeek V3 0324 measured |
| LMArena Text | 1259 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: instruction following | 1235 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: creative writing | 1212 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Vision | 980 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: English | 1276 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: non-English | 1233 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Chinese | 1244 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: German | 1243 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Japanese | 1200 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Korean | 1203 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: French | 1271 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Spanish | 1182 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: Russian | 1240 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: multi-turn | 1246 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: longer queries | 1255 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: writing and language | 1247 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Text: entertainment and media | 1210 | Not measured | Only Nova Pro 1.0 measured |
| LMArena Vision: English | 987 | Not measured | Only Nova Pro 1.0 measured |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nova Pro 1.0 | DeepSeek V3 0324 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
DeepSeek V3 0324 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3 0324 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3 0324 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Amazon Nova Pro 1.0 | DeepSeek V3 0324 |
|---|---|---|
| Maker | Amazon | DeepSeek |
| Weights | No public weights listed | Open weights |
| Released | December 5, 2024 | March 24, 2025 |
| Context window | 300K | 164K |
| Input $/Mtok | $0.80 | $0.27 |
| Output $/Mtok | $3.20 | $1.07 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nova Pro 1.0 better than DeepSeek V3 0324 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nova Pro 1.0 for a larger context window (300K against 164K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
Which is cheaper, Nova Pro 1.0 or DeepSeek V3 0324?
Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 per million output tokens; DeepSeek V3 0324 costs $0.27 and $1.07. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova Pro 1.0 or DeepSeek V3 0324?
Nova Pro 1.0, with 300K tokens against 164K.
How many benchmarks is the Nova Pro 1.0 vs DeepSeek V3 0324 comparison based on?
11 benchmarks have a result for both models as of October 21, 2026. Nova Pro 1.0's coding index rests on 0 independent benchmarks and DeepSeek V3 0324's on 0. Where only one model has a result, the page says so instead of naming a winner.