Compare / DeepSeek vs OpenAI

AI labs compared · November 2026

DeepSeek vs OpenAI: 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. 39 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-1017
27 models on sale with our resultsOpenAI Best: GPT-6.2 Astra · newest: GPT-6.2 Astra
DeepSeek wins 0OpenAI wins 10

Kinds of work led by each lab's best model there, of the 10 both are measured on.

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

DeepSeek or OpenAI? The short answer

OpenAI is ahead: its best models beat DeepSeek's in all 10 kinds of work both are measured on.

  • Pick OpenAI for product listings, decks from an analysis, user surveys, marketing planning, agents and tool use, professional work, reasoning and knowledge, writing, sticking to the facts and speed under pressure.
  • On our overall leaderboard, GPT-6.2 Astra is #2 (86 of 100) and DeepSeek-V4.1-Flash is #21 (49).
  • Prices start at $0.15 per million tokens for DeepSeek (DeepSeek-V4-Flash (0423)) and $0.058 for OpenAI (gpt-oss-20b).

Head to head

49DeepSeek-V4.1-Flash
Best Spring Prompt overall score
86GPT-6.2 Astra
45.1DeepSeek-V4.1-Flash-1017
Best Intelligence Index
52.7GPT-6 Astra
$0.52DeepSeek-V4.1-Flash
Flagship price, per million tokens
$16.00GPT-6.2 Astra
$0.15DeepSeek-V4-Flash (0423)
Cheapest model, per million tokens
$0.058gpt-oss-20b
12
Models on sale with our results
27

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 18 of 35DeepSeek-V4.1-Flash 1 of 35GPT-6.2 Sol
Decks from an analysisTurning a finished analysis into a deck you could present as it is 22 of 35DeepSeek-V4.1-Flash-1017 2 of 35GPT-6 Astra
User surveysPlanning a user survey and reading its results without being misled 12 of 26DeepSeek-V4.1-Flash-1017 2 of 26GPT-6.2 Astra
Marketing planningPlanning a year of ad spend without overspending 23 of 35DeepSeek-V4.1-Flash-1017 2 of 35GPT-6.1 Terra
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 24 of 159DeepSeek-V4.1-Flash-1017 4 of 159GPT-6 Astra
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 29 of 51DeepSeek-V4-Pro (0813) 1 of 51GPT-5.6 Sol
Reasoning and knowledgeHard questions across science, maths and general knowledge 24 of 187DeepSeek-V4.1-Flash-1017 3 of 187GPT-6 Astra
WritingWhat people prefer in blind comparisons, and judged writing quality 29 of 169DeepSeek-V4.1-Flash 15 of 169GPT-5.5
Sticking to the factsSummarising without inventing things, and factual answers 19 of 139DeepSeek-V3.1 18 of 139GPT-6.1 Sol
Speed under pressureGood decisions against a real clock (fast chess) 29 of 38DeepSeek-V4.1-Flash-1017 3 of 38GPT-6.1 Sol

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.

DeepSeekOpenAI

0204060 $0.01$0.1$1$10$100 Price per million tokens, blended (log scale) Intelligence Index DeepSeek-V4.1-Flash-1017GPT-6.1 SolGPT-6 AstraGPT-6 SolGPT-5.6 SolGPT-5.6 Terra

On our overall leaderboard

The 10 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. #2GPT-6.2 Astra86
  2. #3GPT-6.2 Sol84
  3. #5GPT-6.1 Sol78
  4. #6GPT-6.1 Terra77
  5. #7GPT-6 Astra76
  6. #10GPT-6 Sol66
  7. #21DeepSeek-V4.1-Flash49
  8. #27GPT-6 Luna38
  9. #29DeepSeek-V4.1-Flash-101737
  10. #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.

MeasureDeepSeekOpenAI
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 3663.1%o3 · 5 of 36
OpenHands Index · Average% resolved, higher is better 45.7%DeepSeek-V3.2 · 20 of 3165.9%GPT-5.5 · 5 of 31
Microsoft STATE-Bench · Task success (pass@1) · STATE-Bench v0.7% of tasks, higher is better 47.2%DeepSeek-V4-Pro (0423) · 4 of 455.7%GPT-5.4 · 1 of 4
Artificial Analysis · Terminal-Bench 4.0% of tasks, higher is better 33.8%DeepSeek-V4.1-Flash-1017 · 18 of 10759.6%GPT-6 Astra · 3 of 107
Artificial Analysis · Terminal-Bench 2.1% of tasks, higher is better 78.7%DeepSeek-V4-Pro (0813) · 24 of 10789.9%GPT-6 Astra · 2 of 107
Artificial Analysis · τ-bench banking% of tasks, higher is better 39.6%DeepSeek-V4-Pro (0813) · 17 of 10444.3%GPT-5.6 Sol · 12 of 104
Vending-Bench 2 · Money after a yearUS dollars, higher is better $3,285DeepSeek-V4-Pro (0423) · 36 of 53$15,515GPT-6 Astra · 1 of 53
Decks from an analysis
DeckBench · Deck ratingrating, higher is better 1,046DeepSeek-V4.1-Flash-1017 · 22 of 351,551GPT-6 Astra · 2 of 35
Marketing planning
ROASBench · Overall scorescore out of 100, higher is better 41.4DeepSeek-V4.1-Flash-1017 · 23 of 3558.4GPT-6.1 Terra · 2 of 35
Product listings
CatalogBench · Reliably publish-ready% of products, higher is better 41.1%DeepSeek-V4.1-Flash · 20 of 3575.0%GPT-6.2 Sol · 2 of 35
CatalogBench · Reliably publish-ready · sales brief% of products, higher is better 23.2%DeepSeek-V4.1-Flash · 14 of 3575.0%GPT-6.2 Sol · 1 of 35
Professional work
APEX-Agents · Tasks passed% of tasks, higher is better 47.3%DeepSeek-V4-Pro (0813) · 24 of 3764.7%GPT-6 Astra · 7 of 37
Reasoning and knowledge
Artificial Analysis · Artificial Analysis Intelligence Indexindex score, higher is better 45.1DeepSeek-V4.1-Flash-1017 · 16 of 18552.7GPT-6 Astra · 4 of 185
Artificial Analysis · Humanity's Last Exam% of questions, higher is better 43.3%DeepSeek-V4.1-Flash-1017 · 29 of 18654.7%GPT-6 Astra · 7 of 186
Artificial Analysis · GPQA Diamond% of questions, higher is better 92.8%DeepSeek-V4-Pro (0813) · 15 of 16896.3%GPT-6 Astra · 1 of 168
Speed under pressure
BulletBench · Ladder Elo · Bullet 60sladder Elo, higher is better 147DeepSeek-V4.1-Flash-1017 · 28 of 36928GPT-6.1 Sol · 2 of 36
Sticking to the facts
Vectara Hallucination Leaderboard · Hallucination rate · Vectara% of summaries, lower is better 5.3%DeepSeek-V3.2-Exp · 9 of 713.1%GPT-5.4 nano · 1 of 71
Arena (formerly LMArena) · Overall · Text factualityArena rating, higher is better 1,467DeepSeek-V4.1-Flash · 24 of 1091,486GPT-5.5 · 6 of 109
SimpleQA Verified (Epoch AI) · Correct answers% of questions, higher is better 52.9%DeepSeek-V4-Pro (0813) · 20 of 6875.6%GPT-6 Astra · 1 of 68
User surveys
SurveyBench · Analysis ratingrating, higher is better 1,119DeepSeek-V4.1-Flash-1017 · 12 of 261,476GPT-6.2 Astra · 2 of 26
Writing
Arena (formerly LMArena) · Overall · TextArena rating, higher is better 1,474DeepSeek-V4.1-Flash · 27 of 1531,484GPT-5.6 Sol · 15 of 153
UGI Leaderboard · Writing score · UGIscore out of 100, higher is better 68.4DeepSeek-V4-Pro (0423) · 14 of 12469.7GPT-5.5 · 11 of 124

Quick answers

Is DeepSeek or OpenAI better?

OpenAI is ahead: its best models beat DeepSeek's in all 10 kinds of work both are measured on.

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.

What is OpenAI's best model?

GPT-6.2 Astra: #2 on the Spring Prompt overall leaderboard.

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

OpenAI: its best model there, GPT-6 Astra, ranks 4 of 159 models on sale, against 24 for DeepSeek's DeepSeek-V4.1-Flash-1017.

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

OpenAI: its best model there, GPT-6 Astra, ranks 3 of 187 models on sale, against 24 for DeepSeek's DeepSeek-V4.1-Flash-1017.

Which is better for writing, DeepSeek or OpenAI?

OpenAI: its best model there, GPT-5.5, ranks 15 of 169 models on sale, against 29 for DeepSeek's DeepSeek-V4.1-Flash.

Which is cheaper, DeepSeek or OpenAI?

OpenAI's cheapest model with results, gpt-oss-20b, costs $0.058 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 DeepSeek, OpenAI and the rest on your own prompt, and see the cheapest one that passes.