Compare / DeepSeek-V4.1-Flash-1017 vs Gemini 3.6 Flash

DeepSeek-V4.1-Flash-1017 vs Gemini 3.6 Flash

Which is cheaper, which is more capable, and which does better at each kind of work, from 10 results on 2 sources that measured both models.

DeepSeekDeepSeek-V4.1-Flash-1017 Released 17 Oct 2026 · $0.30 in · $1.20 out
GoogleGemini 3.6 Flash Released 21 Jul 2026 · $1.50 in · $7.50 out
DeepSeek-V4.1-Flash-1017 wins 71 too close to callGemini 3.6 Flash wins 2

Of the 10 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 20 October 2026 (catalogue release 2026-10-20-96eb40c3ec63). See also DeepSeek vs Google, every model from both labs.

DeepSeek-V4.1-Flash-1017 or Gemini 3.6 Flash? The short answer

Pick DeepSeek-V4.1-Flash-1017: it scores higher (Intelligence Index 45.1 against 34.0) and costs less.

  • DeepSeek-V4.1-Flash-1017 is cheaper to run: $0.005 against $0.011 per game of bullet chess on BulletBench (2.4 times less).
  • DeepSeek-V4.1-Flash-1017 scores higher on the Artificial Analysis Intelligence Index: 45.1 against 34.0.
  • DeepSeek-V4.1-Flash-1017 is newer: released 17 Oct 2026, against 21 Jul 2026 for Gemini 3.6 Flash.
  • On third-party benchmarks, on the results both models have: DeepSeek-V4.1-Flash-1017 does better for agents and tool use and reasoning and knowledge.

Head to head

45.1
Intelligence Index
34.0
$0.52
Price per million tokens, blendedlower is better
$3.00
1,048,576
Context window, tokens
1,048,576

Every fact side by side

DeepSeek-V4.1-Flash-1017Gemini 3.6 Flash
Price per million tokens$0.30 in · $1.20 out$1.50 in · $7.50 out
Blended (3 in : 1 out)$0.52$3.00
Cheapest host, blended–$1.50 (Google)
Cost per game of bullet chess (BulletBench)$0.005$0.011
Cached input, per million$0.006 cached input–
Intelligence Index45.134.0
Spring Prompt overall44–
Output speed, tokens a second212–
Context window1,048,576 tokens1,048,576 tokens
Released17 Oct 2026 (newer)21 Jul 2026
WeightsOpenClosed
Developer based inChinathe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 21 of 24 not measured
Decks from an analysisTurning a finished analysis into a deck you could present as it is 12 of 24 not measured
User surveysPlanning a user survey and reading its results without being misled 5 of 13 not measured
Marketing planningPlanning a year of ad spend without overspending 11 of 24 not measured
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 22 of 168 52 of 168
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 35 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 22 of 202 35 of 202
WritingWhat people prefer in blind comparisons, and judged writing quality not measured 14 of 189
Sticking to the factsSummarising without inventing things, and factual answers not measured 22 of 153
Speed under pressureGood decisions against a real clock (fast chess) 21 of 27 15 of 27

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureDeepSeek-V4.1-Flash-1017Gemini 3.6 Flash
BulletBench measured by Spring Prompt · 3 results
Cost per game · Bullet 60sUS dollars, lower is better 13 · 19 of 32 measured $0.0047low reasoning $0.0113minimal reasoning
Ladder Elo · Bullet 60sladder Elo, higher is better 27 · 6 of 32 measured 147low reasoning 628minimal reasoning
Games lost on time · Bullet 60s% of games, lower is better 29 · 19 of 32 measured 87.5%low reasoning 41.7%minimal reasoning
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 16 · 45 of 249 measured 45.1max reasoning 34.0high reasoning
Humanity's Last Exam% of questions, higher is better 27 · 41 of 248 measured 43.3%max reasoning 40.8%high reasoning
Terminal-Bench 4.0% of tasks, higher is better 16 · 44 of 118 measured 33.8%max reasoning 7.1%high reasoning
Show all 10 results (4 more)
MeasureDeepSeek-V4.1-Flash-1017Gemini 3.6 Flash
BulletBench measured by Spring Prompt · 2 results
Invalid moves · Bullet 60s% of moves, lower is better 1 · 25 of 32 measured 0.0%low reasoning 0.3%minimal reasoning
Median move time · Bullet 60smilliseconds, lower is better 31 · 22 of 32 measured 3.3 slow reasoning 1.6 sminimal reasoning
Artificial Analysis reported by Artificial Analysis · 2 results
Long-context reasoning (AA-LCR)% of questions, higher is better 19 · 40 of 239 measured 82.7%max reasoning 80.0%high reasoning
SciCode% of problems, higher is better 24 · 36 of 119 measured 55.9%max reasoning 53.4%high reasoning

Quick answers

Is DeepSeek-V4.1-Flash-1017 better than Gemini 3.6 Flash?

Pick DeepSeek-V4.1-Flash-1017: it scores higher (Intelligence Index 45.1 against 34.0) and costs less.

Which is cheaper, DeepSeek-V4.1-Flash-1017 or Gemini 3.6 Flash?

DeepSeek-V4.1-Flash-1017 is cheaper to run: $0.005 against $0.011 per game of bullet chess on BulletBench (2.4 times less).

Which is better for agents and tool use, DeepSeek-V4.1-Flash-1017 or Gemini 3.6 Flash?

DeepSeek-V4.1-Flash-1017 ranks 22 of 168 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 52 for Gemini 3.6 Flash.

Which is better for reasoning and knowledge, DeepSeek-V4.1-Flash-1017 or Gemini 3.6 Flash?

DeepSeek-V4.1-Flash-1017 ranks 22 of 202 models on sale for hard questions across science, maths and general knowledge, against 35 for Gemini 3.6 Flash.

Which is better for speed under pressure, DeepSeek-V4.1-Flash-1017 or Gemini 3.6 Flash?

Gemini 3.6 Flash ranks 15 of 27 models on sale for good decisions against a real clock (fast chess), against 21 for DeepSeek-V4.1-Flash-1017.

Run DeepSeek-V4.1-Flash-1017 and Gemini 3.6 Flash on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.

Try the playgroundTalk to us