Enter opens the highlighted result. Esc closes.

Nova Pro 1.0 vs DeepSeek V3.1 Terminus

DeepSeek V3.1 Terminus leads Nova Pro 1.0 on the Artificial Analysis Intelligence Index, 14.8 to 7.0, and DeepSeek V3.1 Terminus costs 3.2x less per output token ($1.0142 vs $3.20 per million). Updated October 21, 2026; 31 benchmarks have a result for both.

Replace Nova Pro 1.0 Replace DeepSeek V3.1 Terminus
Nova Pro 1.0Amazon
Coding
No data
Overall
7.0
Output $/M
$3.20
0
DeepSeek V3.1 TerminusDeepSeek
Coding
No data
Overall
14.8
Output $/M
$1.0142
31
vs boards won of 31 shared

Nova Pro 1.0 or DeepSeek V3.1 Terminus: 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.

Model ANova Pro 1.0AmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BDeepSeek V3.1 TerminusDeepSeekNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
31
Nova Pro 1.0 only
11
DeepSeek V3.1 Terminus only
13
Like-for-like categories
8 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.

At a glance

Coding index
Nova Pro 1.0 not benchmarked, DeepSeek V3.1 Terminus not benchmarked.
Widest category
Math, 63.5 points apart on average over 3 shared benchmarks.
Widest single gap
AA Math Index: Nova Pro 1.0 7.0 against DeepSeek V3.1 Terminus 89.7, 82.7 points apart on a 0 to 100 scale.
Output price
Nova Pro 1.0 $3.20 against DeepSeek V3.1 Terminus $1.0142 per million output tokens, 3.2x apart.
Context window
Nova Pro 1.0 takes 300K tokens, DeepSeek V3.1 Terminus 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.

Boards won, where both have a result
CategoryNova Pro 1.0BarsDeepSeek V3.1 TerminusTies
Coding04
Intelligence01
Agentic work01
Reasoning04
Math03
Knowledge05
Web design01
General012
All shared boards031
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
AA Coding IndexNot measured43.5Only DeepSeek V3.1 Terminus measured
LiveCodeBench (Artificial Analysis run)23.3%79.8%DeepSeek V3.1 Terminus
SciCodeNot measured38.0%Only DeepSeek V3.1 Terminus measured
Terminal-Bench Hard (Artificial Analysis run)6.1%31.8%DeepSeek V3.1 Terminus
ALE-BenchNot measured745.2Only DeepSeek V3.1 Terminus measured
LMArena Text: coding12701425DeepSeek V3.1 Terminus
LMArena Text: software and IT12711426DeepSeek V3.1 Terminus
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
AA Intelligence Index7.014.8DeepSeek V3.1 Terminus
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
AA Agentic IndexNot measured6.8Only DeepSeek V3.1 Terminus measured
τ²-Bench Telecom14.0%37.1%DeepSeek V3.1 Terminus
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
GPQA Diamond (Artificial Analysis run)49.9%79.2%DeepSeek V3.1 Terminus
Humanity's Last Exam (Artificial Analysis run)3.2%16.4%DeepSeek V3.1 Terminus
LMArena Text: hard prompts12461426DeepSeek V3.1 Terminus
LMArena Text: expert1211Not measuredOnly Nova Pro 1.0 measured
LMArena Text: hard prompts in English12591432DeepSeek V3.1 Terminus
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
AA Math Index7.089.7DeepSeek V3.1 Terminus
AIME 2025 (Artificial Analysis run)7.0%89.7%DeepSeek V3.1 Terminus
LMArena Text: math12521402DeepSeek V3.1 Terminus
LMArena Text: mathematical work1261Not measuredOnly Nova Pro 1.0 measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
MMLU Pro (Artificial Analysis run)69.1%85.1%DeepSeek V3.1 Terminus
MMLU82.0%Not measuredOnly Nova Pro 1.0 measured
LMArena Text: science12551451DeepSeek V3.1 Terminus
LMArena Text: medicine and healthcare12601468DeepSeek V3.1 Terminus
LMArena Text: legal and government12811457DeepSeek V3.1 Terminus
LMArena Text: business and finance12291414DeepSeek V3.1 Terminus
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index01
Web design benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
Design Arena: websites7961187DeepSeek V3.1 Terminus
Design Arena: UI componentsNot measured1182Only DeepSeek V3.1 Terminus measured
Design Arena: game devNot measured1131Only DeepSeek V3.1 Terminus measured
Design Arena: data vizNot measured1167Only DeepSeek V3.1 Terminus measured
Design Arena: 3DNot measured1141Only DeepSeek V3.1 Terminus measured
Design Arena: all code categoriesNot measured1175Only DeepSeek V3.1 Terminus measured
Design Arena: SVGNot measured1065Only DeepSeek V3.1 Terminus measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index012
General benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
IFBench38.1%57.0%DeepSeek V3.1 Terminus
Long context reasoning (AA-LCR)21.0%69.3%DeepSeek V3.1 Terminus
DTBenchNot measured81.3%Only DeepSeek V3.1 Terminus measured
LMCANot measured28.6%Only DeepSeek V3.1 Terminus measured
LMArena Text12591419DeepSeek V3.1 Terminus
LMArena Text: instruction following12351404DeepSeek V3.1 Terminus
LMArena Text: creative writing12121403DeepSeek V3.1 Terminus
LMArena Vision980Not measuredOnly Nova Pro 1.0 measured
LMArena Text: English12761429DeepSeek V3.1 Terminus
LMArena Text: non-English12331408DeepSeek V3.1 Terminus
LMArena Text: Chinese1244Not measuredOnly Nova Pro 1.0 measured
LMArena Text: German1243Not measuredOnly Nova Pro 1.0 measured
LMArena Text: Japanese1200Not measuredOnly Nova Pro 1.0 measured
LMArena Text: Korean1203Not measuredOnly Nova Pro 1.0 measured
LMArena Text: French1271Not measuredOnly Nova Pro 1.0 measured
LMArena Text: Spanish1182Not measuredOnly Nova Pro 1.0 measured
LMArena Text: Russian12401435DeepSeek V3.1 Terminus
LMArena Text: PolishNot measured1427Only DeepSeek V3.1 Terminus measured
LMArena Text: multi-turn12461411DeepSeek V3.1 Terminus
LMArena Text: longer queries12551422DeepSeek V3.1 Terminus
LMArena Text: writing and language12471409DeepSeek V3.1 Terminus
LMArena Text: entertainment and media12101391DeepSeek V3.1 Terminus
LMArena Vision: English987Not measuredOnly Nova Pro 1.0 measured
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Nova Pro 1.0 and DeepSeek V3.1 Terminus
BenchmarkNova Pro 1.0DeepSeek V3.1 TerminusLeader
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

Nova Pro 1.0$0.0024Fits in one request
DeepSeek V3.1 Terminus$0.0008Fits in one request

DeepSeek V3.1 Terminus costs less

Repository review

50K input + 3K output tokens

Nova Pro 1.0$0.050Fits in one request
DeepSeek V3.1 Terminus$0.018Fits in one request

DeepSeek V3.1 Terminus costs less

Agent loop

200K input + 10K output tokens

Nova Pro 1.0$0.192Fits in one request
DeepSeek V3.1 Terminus$0.071Exceeds the context window

DeepSeek V3.1 Terminus 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.

Specifications of Nova Pro 1.0 and DeepSeek V3.1 Terminus
SpecificationAmazon Nova Pro 1.0DeepSeek V3.1 Terminus
MakerAmazonDeepSeek
WeightsNo public weights listedOpen weights
ReleasedDecember 5, 2024September 22, 2025
Context window300K164K
Input $/Mtok$0.80$0.3063
Output $/Mtok$3.20$1.0142
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Nova Pro 1.0 better than DeepSeek V3.1 Terminus 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 V3.1 Terminus?

Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 per million output tokens; DeepSeek V3.1 Terminus costs $0.3063 and $1.0142. Cost per solved task is known for neither of them.

Which has the bigger context window, Nova Pro 1.0 or DeepSeek V3.1 Terminus?

Nova Pro 1.0, with 300K tokens against 164K.

How many benchmarks is the Nova Pro 1.0 vs DeepSeek V3.1 Terminus comparison based on?

31 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 V3.1 Terminus's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next