Compare / DeepSeek vs Google

AI labs compared · October 2026

DeepSeek vs Google: 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. 28 models in all; a lab is only as good as the model you would actually pick from it.

12 models on sale with our resultsDeepSeek Best: DeepSeek-V4.1-Flash · newest: DeepSeek-V4.1-Flash
16 models on sale with our resultsGoogle Best: Gemini 3.8 Flash · newest: Gemini 3.8 Flash
DeepSeek wins 2Google wins 6

Kinds of work led by each lab's best model there, of the 8 both are measured on.

Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe). Models on sale means listed on OpenRouter today.

DeepSeek or Google? The short answer

Google is ahead: its best models beat DeepSeek's in 6 of the 8 kinds of work both are measured on; DeepSeek leads in 2.

  • Pick DeepSeek for product listings and agents and tool use.
  • Pick Google for decks from an analysis, marketing planning, professional work, reasoning and knowledge, writing and sticking to the facts.
  • On our overall leaderboard, Gemini 3.8 Flash is #8 (61 of 100) and DeepSeek-V4.1-Flash is #9 (56).
  • Prices start at $0.18 per million tokens for DeepSeek (DeepSeek-V4-Flash (0731)) and $0.062 for Google (Gemma 3 4B).

Head to head

56DeepSeek-V4.1-Flash
Best Spring Prompt overall score
61Gemini 3.8 Flash
39.5DeepSeek-V4.1-Flash
Best Intelligence Index
40.9Gemini 3.8 Flash
$0.52DeepSeek-V4.1-Flash
Flagship price, per million tokens
$3.00Gemini 3.8 Flash
$0.18DeepSeek-V4-Flash (0731)
Cheapest model, per million tokens
$0.062Gemma 3 4B
12
Models on sale with our results
16

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 7 of 20DeepSeek-V4.1-Flash 8 of 20Gemini 3.1 Pro Preview
Decks from an analysisTurning a finished analysis into a deck you could present as it is 18 of 19DeepSeek-V4-Pro (0423) 12 of 19Gemini 3.8 Flash
User surveysPlanning a user survey and reading its results without being misled not measured 5 of 8Gemini 3.1 Pro Preview
Marketing planningPlanning a year of ad spend without overspending 13 of 19DeepSeek-V4-Pro (0423) 7 of 19Gemini 3.8 Flash
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 21 of 164DeepSeek-V4.1-Flash 29 of 164Gemini 3.7 Flash
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 29 of 51DeepSeek-V4-Pro (0813) 11 of 51Gemini 3.8 Flash
Reasoning and knowledgeHard questions across science, maths and general knowledge 29 of 198DeepSeek-V4-Pro (0813) 12 of 198Gemini 3.8 Flash
WritingWhat people prefer in blind comparisons, and judged writing quality 28 of 188DeepSeek-V4.1-Flash 2 of 188Gemini 3.8 Flash
Sticking to the factsSummarising without inventing things, and factual answers 20 of 152DeepSeek-V3.1 1 of 152Gemini 2.5 Flash-Lite
Speed under pressureGood decisions against a real clock (fast chess) not measured 2 of 22Gemini 3.5 Flash-Lite

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.

DeepSeekGoogle

01020304050 $0.01$0.1$1$10 Price per million tokens, blended (log scale) Intelligence Index DeepSeek-V4.1-FlashDeepSeek-V4-Pro (0813)DeepSeek-V4-Flash (0731)Gemini 3.8 FlashGemini 3.7 FlashGemini 3.6 Flash

On our overall leaderboard

The 5 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. #8Gemini 3.8 Flash61
  2. #9DeepSeek-V4.1-Flash56
  3. #10Gemini 3.1 Pro Preview50
  4. #18DeepSeek-V4-Pro (0423)33
  5. #19Gemini 3.5 Flash-Lite27

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.

MeasureDeepSeekGoogle
Agents and tool use
Berkeley Function Calling Leaderboard (BFCL) V4 · Overall accuracy · BFCL% correct, higher is better 56.7%DeepSeek-V3.2-Exp · 7 of 3856.2%Gemini 2.5 Flash · 8 of 38
OpenHands Index · Average% resolved, higher is better 45.7%DeepSeek-V3.2 · 20 of 3362.6%Gemini 3.5 Flash · 7 of 33
Artificial Analysis · Terminal-Bench 4.0% of tasks, higher is better 26.8%DeepSeek-V4.1-Flash · 17 of 10519.7%Gemini 3.8 Flash · 23 of 105
Artificial Analysis · Terminal-Bench 2.1% of tasks, higher is better 78.7%DeepSeek-V4-Pro (0813) · 24 of 11587.6%Gemini 3.8 Flash · 8 of 115
Artificial Analysis · τ-bench banking% of tasks, higher is better 39.6%DeepSeek-V4-Pro (0813) · 17 of 11345.8%Gemini 3.8 Flash · 10 of 113
Vending-Bench 2 · Money after a yearUS dollars, higher is better $3,285DeepSeek-V4-Pro (0423) · 37 of 56$5,396Gemini 3.5 Flash · 22 of 56
Decks from an analysis
DeckBench · Deck ratingrating, higher is better 613DeepSeek-V4-Pro (0423) · 18 of 19894Gemini 3.8 Flash · 12 of 19
Marketing planning
ROASBench · Overall scorescore out of 100, higher is better 28.3DeepSeek-V4-Pro (0423) · 13 of 1951.4Gemini 3.8 Flash · 7 of 19
Product listings
CatalogBench · Reliably publish-ready% of products, higher is better 41.1%DeepSeek-V4.1-Flash · 9 of 2044.6%Gemini 3.1 Pro Preview · 8 of 20
CatalogBench · Reliably publish-ready · sales brief% of products, higher is better 23.2%DeepSeek-V4.1-Flash · 6 of 2016.1%Gemini 3.1 Pro Preview · 8 of 20
Professional work
APEX-Agents · Tasks passed% of tasks, higher is better 47.3%DeepSeek-V4-Pro (0813) · 24 of 3767.8%Gemini 3.7 Flash · 4 of 37
Reasoning and knowledge
Artificial Analysis · Artificial Analysis Intelligence Indexindex score, higher is better 39.5DeepSeek-V4.1-Flash · 26 of 19840.9Gemini 3.8 Flash · 21 of 198
Artificial Analysis · Humanity's Last Exam% of questions, higher is better 41.0%DeepSeek-V4-Pro (0813) · 34 of 19747.9%Gemini 3.7 Flash · 12 of 197
Artificial Analysis · GPQA Diamond% of questions, higher is better 92.8%DeepSeek-V4-Pro (0813) · 15 of 18795.3%Gemini 3.8 Flash · 2 of 187
Sticking to the facts
Vectara Hallucination Leaderboard · Hallucination rate · Vectara% of summaries, lower is better 5.3%DeepSeek-V3.2-Exp · 10 of 793.3%Gemini 2.5 Flash-Lite · 2 of 79
Arena (formerly LMArena) · Overall · Text factualityArena rating, higher is better 1,467DeepSeek-V4.1-Flash · 23 of 1131,477Gemini 3.7 Flash · 12 of 113
SimpleQA Verified (Epoch AI) · Correct answers% of questions, higher is better 52.9%DeepSeek-V4-Pro (0813) · 20 of 7373.5%Gemini 3.1 Pro Preview · 3 of 73
Writing
Arena (formerly LMArena) · Overall · TextArena rating, higher is better 1,474DeepSeek-V4.1-Flash · 26 of 1661,495Gemini 3.8 Flash · 6 of 166
UGI Leaderboard · Writing score · UGIscore out of 100, higher is better 68.4DeepSeek-V4-Pro (0423) · 14 of 13878.6Gemini 3.8 Flash · 1 of 138

Their models, one against one

Quick answers

Is DeepSeek or Google better?

Google is ahead: its best models beat DeepSeek's in 6 of the 8 kinds of work both are measured on; DeepSeek leads in 2.

What is DeepSeek's best model?

DeepSeek-V4.1-Flash: #9 on the Spring Prompt overall leaderboard and 39.5 on the Artificial Analysis Intelligence Index.

What is Google's best model?

Gemini 3.8 Flash: #8 on the Spring Prompt overall leaderboard and 40.9 on the Artificial Analysis Intelligence Index.

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

DeepSeek: its best model there, DeepSeek-V4.1-Flash, ranks 21 of 164 models on sale, against 29 for Google's Gemini 3.7 Flash.

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

Google: its best model there, Gemini 3.8 Flash, ranks 12 of 198 models on sale, against 29 for DeepSeek's DeepSeek-V4-Pro (0813).

Which is better for writing, DeepSeek or Google?

Google: its best model there, Gemini 3.8 Flash, ranks 2 of 188 models on sale, against 28 for DeepSeek's DeepSeek-V4.1-Flash.

Which is cheaper, DeepSeek or Google?

Google's cheapest model with results, Gemma 3 4B, costs $0.062 per million tokens (three input to one output), against $0.18 for DeepSeek-V4-Flash (0731) from DeepSeek.

Other labs compared

Which model is best for your product?

Benchmarks aren't your data. We test the models from DeepSeek, Google and the rest on your own tasks, with the cost of every answer.

Talk to usSee the leaderboard