Compare / Amazon vs DeepSeek

AI labs compared · November 2026

Amazon vs DeepSeek: which AI lab is ahead?

Each lab's best model on sale goes head to head on every kind of work we measure, from our own benchmarks and licensed sources. 16 models in all; a lab is only as good as the model you would actually pick from it.

4 models on sale with our resultsAmazon Best: Nova 2 Lite · newest: Nova 2 Lite
12 models on sale with our resultsDeepSeek Best: DeepSeek-V4.1-Flash · newest: DeepSeek-V4.1-Flash-1017
Amazon wins 1DeepSeek wins 3

Kinds of work led by each lab's best model there, of the 4 both are measured on.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331). Models on sale means listed on OpenRouter today.

Amazon or DeepSeek? The short answer

DeepSeek is ahead: its best models beat Amazon's in 3 of the 4 kinds of work both are measured on; Amazon leads in 1.

  • Pick Amazon for sticking to the facts.
  • Pick DeepSeek for agents and tool use, reasoning and knowledge and writing.
  • DeepSeek's DeepSeek-V4.1-Flash is #21 on our overall leaderboard; no Amazon model has enough of our results to be ranked there yet.
  • Prices start at $0.061 per million tokens for Amazon (Nova Micro 1.0) and $0.15 for DeepSeek (DeepSeek-V4-Flash (0423)).

Head to head

13.4Nova 2 Lite
Best Intelligence Index
45.1DeepSeek-V4.1-Flash-1017
$0.85Nova 2 Lite
Flagship price, per million tokens
$0.52DeepSeek-V4.1-Flash
$0.061Nova Micro 1.0
Cheapest model, per million tokens
$0.15DeepSeek-V4-Flash (0423)
4
Models on sale with our results
12

Each line names the model behind the number. Prices are blended, three input tokens to one output, at the developer's list price where we have read it; see every model's price. Intelligence Index from Artificial Analysis; overall score from our leaderboard.

Which lab is better for what

For each kind of work, each lab's best model there and its rank among every model on sale. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live not measured 18 of 35DeepSeek-V4.1-Flash
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 22 of 35DeepSeek-V4.1-Flash-1017
User surveysPlanning a user survey and reading its results without being misled not measured 12 of 26DeepSeek-V4.1-Flash-1017
Marketing planningPlanning a year of ad spend without overspending not measured 23 of 35DeepSeek-V4.1-Flash-1017
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 131 of 159Nova 2 Lite 24 of 159DeepSeek-V4.1-Flash-1017
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 29 of 51DeepSeek-V4-Pro (0813)
Reasoning and knowledgeHard questions across science, maths and general knowledge 117 of 187Nova 2 Lite 24 of 187DeepSeek-V4.1-Flash-1017
WritingWhat people prefer in blind comparisons, and judged writing quality 154 of 169Nova 2 Lite 29 of 169DeepSeek-V4.1-Flash
Sticking to the factsSummarising without inventing things, and factual answers 8 of 139Nova Pro 1.0 19 of 139DeepSeek-V3.1
Speed under pressureGood decisions against a real clock (fast chess) not measured 29 of 38DeepSeek-V4.1-Flash-1017

Every model, by intelligence and price

Each dot is a model on sale with an Intelligence Index from Artificial Analysis. Up is smarter; left is cheaper. Hover or tap a dot for its name.

AmazonDeepSeek

01020304050 $0.01$0.1$1$10 Price per million tokens, blended (log scale) Intelligence Index DeepSeek-V4.1-FlashDeepSeek-V4.1-Flash-1017DeepSeek-V4-Pro (0423)DeepSeek-V4-Pro (0813)DeepSeek-V4-Flash (0731)DeepSeek-V4-Flash (0423)

On our overall leaderboard

The 3 of their models we rank overall: one score out of 100 across everything we publish (how the score works). Only models with enough of our own results are ranked.

  1. #21DeepSeek-V4.1-Flash49
  2. #29DeepSeek-V4.1-Flash-101737
  3. #34DeepSeek-V4-Pro (0423)27

Benchmark by benchmark

The headline result of every benchmark both labs have models on: each lab's best model and its rank among the models on sale. Green marks the better rank.

MeasureAmazonDeepSeek
Agents and tool use
Berkeley Function Calling Leaderboard (BFCL) V4 · Overall accuracy · BFCL% correct, higher is better 27.1%Nova 2 Lite · 30 of 3656.7%DeepSeek-V3.2-Exp · 7 of 36
Artificial Analysis · Terminal-Bench 2.1% of tasks, higher is better 16.1%Nova 2 Lite · 84 of 10778.7%DeepSeek-V4-Pro (0813) · 24 of 107
Reasoning and knowledge
Artificial Analysis · Artificial Analysis Intelligence Indexindex score, higher is better 13.4Nova 2 Lite · 117 of 18545.1DeepSeek-V4.1-Flash-1017 · 16 of 185
Artificial Analysis · Humanity's Last Exam% of questions, higher is better 11.6%Nova 2 Lite · 122 of 18643.3%DeepSeek-V4.1-Flash-1017 · 29 of 186
Artificial Analysis · GPQA Diamond% of questions, higher is better 81.1%Nova 2 Lite · 90 of 16892.8%DeepSeek-V4-Pro (0813) · 15 of 168
Sticking to the facts
Vectara Hallucination Leaderboard · Hallucination rate · Vectara% of summaries, lower is better 5.1%Nova 2 Lite · 5 of 715.3%DeepSeek-V3.2-Exp · 9 of 71
Arena (formerly LMArena) · Overall · Text factualityArena rating, higher is better 1,380Nova 2 Lite · 104 of 1091,467DeepSeek-V4.1-Flash · 24 of 109
Writing
Arena (formerly LMArena) · Overall · TextArena rating, higher is better 1,335Nova 2 Lite · 126 of 1531,474DeepSeek-V4.1-Flash · 27 of 153
UGI Leaderboard · Writing score · UGIscore out of 100, higher is better 23.5Nova 2 Lite · 121 of 12468.4DeepSeek-V4-Pro (0423) · 14 of 124

Quick answers

Is Amazon or DeepSeek better?

DeepSeek is ahead: its best models beat Amazon's in 3 of the 4 kinds of work both are measured on; Amazon leads in 1.

What is Amazon's best model?

Nova 2 Lite: 13.4 on the Artificial Analysis Intelligence Index.

What is DeepSeek's best model?

DeepSeek-V4.1-Flash: #21 on the Spring Prompt overall leaderboard and 39.5 on the Artificial Analysis Intelligence Index.

Which is better for agents and tool use, Amazon or DeepSeek?

DeepSeek: its best model there, DeepSeek-V4.1-Flash-1017, ranks 24 of 159 models on sale, against 131 for Amazon's Nova 2 Lite.

Which is better for reasoning and knowledge, Amazon or DeepSeek?

DeepSeek: its best model there, DeepSeek-V4.1-Flash-1017, ranks 24 of 187 models on sale, against 117 for Amazon's Nova 2 Lite.

Which is better for writing, Amazon or DeepSeek?

DeepSeek: its best model there, DeepSeek-V4.1-Flash, ranks 29 of 169 models on sale, against 154 for Amazon's Nova 2 Lite.

Which is cheaper, Amazon or DeepSeek?

Amazon's cheapest model with results, Nova Micro 1.0, costs $0.061 per million tokens (three input to one output), against $0.15 for DeepSeek-V4-Flash (0423) from DeepSeek.

Other labs compared

Which model is best for your product?

Benchmarks aren't your task. Run models from Amazon, DeepSeek and the rest on your own prompt, and see the cheapest one that passes.