Noometry

Model comparison

Amazon Nova Pro vs DeepSeek-V3.1-Terminus

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 31.0 on the Noometry Index.

Last verified . 10 shared benchmarks.

Amazon Nova Pro Amazon

31.0

Rank #281 Confirmed

DeepSeek-V3.1-Terminus DeepSeek

43.1

Rank #97 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and DeepSeek-V3.1-Terminus in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 43.9.
  • DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
  • Amazon Nova Pro accepts more context: 300K tokens versus 164K.
  • DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

Side by side

Amazon Nova ProDeepSeek-V3.1-Terminus
ProviderAmazonDeepSeek
Noometry Index31.043.1
Released2024-12-032025-09-22
WeightsProprietaryOpen
Context window300K164K
Max output10K147K
Input $ / M tokens$0.80$0.27
Output $ / M tokens$3.20$1
Results tracked3816

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding DeepSeek-V3.1-Terminus leads

Amazon Nova Pro: 35.1 (#229), DeepSeek-V3.1-Terminus: 42.0 (#113)

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
LMArena Coding12701426
SciCode—40.6%
LiveBench Coding38.1%—
ALE-Bench—745.17

Agentic & Tool Use Not comparable

Amazon Nova Pro: 16.7 (#147), DeepSeek-V3.1-Terminus: —

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
Berkeley Function Calling Leaderboard25%—
TheAgentCompany1.7%—

Reasoning DeepSeek-V3.1-Terminus leads

Amazon Nova Pro: 20.0 (#243), DeepSeek-V3.1-Terminus: 26.4 (#133)

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
LMArena Hard Prompts12461426
Kagi LLM Benchmark—57.4%
CritPt—1.7%
LiveBench Reasoning32.6%—
DTBench—81.3%
LiveBench Data Analysis48.3%—
LMCA—28.6%
Epoch Capabilities Index123.8—
LiveBench43.5%—

Math DeepSeek-V3.1-Terminus leads

Amazon Nova Pro: 28.5 (#243), DeepSeek-V3.1-Terminus: 38.5 (#137)

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
LMArena Math12521402
Omni-MATH24.2%—
LiveBench Math38%—

Knowledge Not comparable

Amazon Nova Pro: 27.4 (#250), DeepSeek-V3.1-Terminus: —

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
Humanity's Last Exam4.4%—
MMLU-Pro67.3%—
Confabulations30.1%—
Vectara Hallucination Rate5.1%—
GPQA (HELM)44.6%—
LMArena Expert1211—
MMLU82%—

Multimodal Not comparable

Amazon Nova Pro: 25.0 (#126), DeepSeek-V3.1-Terminus: —

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
LMArena Vision980—

Multilingual DeepSeek-V3.1-Terminus leads

Amazon Nova Pro: 39.7 (#223), DeepSeek-V3.1-Terminus: 52.1 (#92)

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
LMArena Non-English12341407
LMArena Russian12401436
LMArena Chinese1244—
LMArena French1271—
LMArena German1243—
LMArena Japanese1200—
LMArena Korean1203—
LMArena Spanish1182—

Instruction Following DeepSeek-V3.1-Terminus leads

Amazon Nova Pro: 64.9 (#226), DeepSeek-V3.1-Terminus: 74.0 (#106)

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
LMArena Instruction Following12351404
LiveBench Instruction Following67.1%—
IFEval81.5%—

Long Context DeepSeek-V3.1-Terminus leads

Amazon Nova Pro: 38.1 (#205), DeepSeek-V3.1-Terminus: 43.4 (#97)

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
LMArena Longer Query12551421

Writing & Preference DeepSeek-V3.1-Terminus leads

Amazon Nova Pro: 43.9 (#226), DeepSeek-V3.1-Terminus: 61.0 (#92)

BenchmarkAmazon Nova ProDeepSeek-V3.1-Terminus
LMArena Text12591419
LMArena Creative Writing12121403
LMArena Multi-Turn12461411
Short-Story Creative Writing60.5%—
WildBench77.7%—
LiveBench Language37%—

Frequently asked questions

Is Amazon Nova Pro better than DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 31.0 on the Noometry Index.

Which is cheaper, Amazon Nova Pro or DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

Is Amazon Nova Pro or DeepSeek-V3.1-Terminus better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 35.1 in the Noometry coding category.

Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 164K.

How many benchmarks do Amazon Nova Pro and DeepSeek-V3.1-Terminus share?

10 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.

Related comparisons

Go deeper