Compare / DeepSeek-V4-Flash (0423) vs Gemini 3.5 Flash-Lite

DeepSeek-V4-Flash (0423) vs Gemini 3.5 Flash-Lite

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 2 sources that measured both models.

DeepSeekDeepSeek-V4-Flash (0423) Released 24 Apr 2026 · $0.050 in · $0.45 out
GoogleGemini 3.5 Flash-Lite Released 21 Jul 2026 · $0.30 in · $2.50 out
DeepSeek-V4-Flash (0423) wins 83 too close to callGemini 3.5 Flash-Lite wins 5

Of the 16 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also DeepSeek vs Google, every model from both labs.

DeepSeek-V4-Flash (0423) or Gemini 3.5 Flash-Lite? The short answer

Pick DeepSeek-V4-Flash (0423): it scores higher (Intelligence Index 24.4 against 22.2) and costs less.

  • DeepSeek-V4-Flash (0423) is cheaper: $0.15 against $0.85 per million tokens, 5.7 times less.
  • DeepSeek-V4-Flash (0423) scores higher on the Artificial Analysis Intelligence Index: 24.4 against 22.2.
  • Gemini 3.5 Flash-Lite is newer: released 21 Jul 2026, against 24 Apr 2026 for DeepSeek-V4-Flash (0423).
  • On third-party benchmarks, on the results both models have: DeepSeek-V4-Flash (0423) does better for agents and tool use and reasoning and knowledge; Gemini 3.5 Flash-Lite for writing and sticking to the facts.

Head to head

24.4
Intelligence Index
22.2
$0.15
Price per million tokens, blendedlower is better
$0.85
1,048,576
Context window, tokens
1,048,576

Every fact side by side

DeepSeek-V4-Flash (0423)Gemini 3.5 Flash-Lite
Price per million tokens$0.050 in · $0.45 out$0.30 in · $2.50 out
Blended (3 in : 1 out)$0.15$0.85
Cheapest host, blended$0.10 (StreamLake, FP8)$0.85 (Google)
Cached input, per million–$0.030 cached input
Intelligence Index24.422.2
Spring Prompt overall–25
Output speed, tokens a second–398
Context window1,048,576 tokens1,048,576 tokens
Released24 Apr 202621 Jul 2026 (newer)
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 not measured 25 of 32
Decks from an analysisTurning a finished analysis into a deck you could present as it is not measured 29 of 32
User surveysPlanning a user survey and reading its results without being misled not measured 19 of 23
Marketing planningPlanning a year of ad spend without overspending not measured 28 of 32
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 59 of 159 81 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 46 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 69 of 187 98 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 63 of 169 49 of 169
Sticking to the factsSummarising without inventing things, and factual answers 81 of 139 61 of 139
Speed under pressureGood decisions against a real clock (fast chess) not measured 2 of 35

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-Flash (0423)Gemini 3.5 Flash-Lite
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 85 · 61 of 387 measured 1,438high reasoning 1,455
Overall · Text factualityArena rating, higher is better 81 · 63 of 163 measured 1,439 1,447
Business, management and finance · TextArena rating, higher is better 91 · 63 of 380 measured 1,439 1,452
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 85 · 97 of 249 measured 24.4high reasoning 22.2
GPQA Diamond% of questions, higher is better 52 · 91 of 232 measured 89.4%max reasoning 83.8%
Humanity's Last Exam% of questions, higher is better 67 · 122 of 250 measured 34.8%max reasoning 18.8%
Show all 16 results (10 more)
MeasureDeepSeek-V4-Flash (0423)Gemini 3.5 Flash-Lite
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 78 · 52 of 385 measured 1,410high reasoning 1,436
Expert prompts · TextArena rating, higher is better 83 · 78 of 338 measured 1,466high reasoning 1,470
Instruction following · TextArena rating, higher is better 79 · 67 of 387 measured 1,433high reasoning 1,443
Writing, literature and language · TextArena rating, higher is better 78 · 56 of 386 measured 1,422high reasoning 1,443
Artificial Analysis reported by Artificial Analysis · 6 results
Terminal-Bench 2.1% of tasks, higher is better 46 · 58 of 131 measured 61.8%max reasoning 53.6%
Terminal-Bench 4.0% of tasks, higher is better 52 · 59 of 120 measured 3.0%high reasoning 1.0%
τ-bench banking% of tasks, higher is better 34 · 52 of 121 measured 30.9%max reasoning 17.5%
Artificial Analysis Coding Indexindex score, higher is better 45 · 58 of 130 measured 56.2max reasoning 49.3
Long-context reasoning (AA-LCR)% of questions, higher is better 89 · 80 of 241 measured 74.3%max reasoning 76.0%
SciCode% of problems, higher is better 73 · 83 of 121 measured 45.3%max reasoning 41.3%

Quick answers

Is DeepSeek-V4-Flash (0423) better than Gemini 3.5 Flash-Lite?

Pick DeepSeek-V4-Flash (0423): it scores higher (Intelligence Index 24.4 against 22.2) and costs less.

Which is cheaper, DeepSeek-V4-Flash (0423) or Gemini 3.5 Flash-Lite?

DeepSeek-V4-Flash (0423) is cheaper: $0.15 against $0.85 per million tokens, 5.7 times less.

Which is better for agents and tool use, DeepSeek-V4-Flash (0423) or Gemini 3.5 Flash-Lite?

DeepSeek-V4-Flash (0423) ranks 59 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 81 for Gemini 3.5 Flash-Lite.

Which is better for reasoning and knowledge, DeepSeek-V4-Flash (0423) or Gemini 3.5 Flash-Lite?

DeepSeek-V4-Flash (0423) ranks 69 of 187 models on sale for hard questions across science, maths and general knowledge, against 98 for Gemini 3.5 Flash-Lite.

Which is better for writing, DeepSeek-V4-Flash (0423) or Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite ranks 49 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 63 for DeepSeek-V4-Flash (0423).

Which is better for sticking to the facts, DeepSeek-V4-Flash (0423) or Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite ranks 61 of 139 models on sale for summarising without inventing things, and factual answers, against 81 for DeepSeek-V4-Flash (0423).

Run DeepSeek-V4-Flash (0423) and Gemini 3.5 Flash-Lite on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.