Compare / DeepSeek-V4-Flash (0423) vs Gemini 3 Pro Preview

DeepSeek-V4-Flash (0423) vs Gemini 3 Pro Preview

Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 3 sources that measured both models.

DeepSeekDeepSeek-V4-Flash (0423) Released 24 Apr 2026 · $0.050 in · $0.45 out
GoogleGemini 3 Pro Preview Released 18 Nov 2025 · Not on sale
DeepSeek-V4-Flash (0423) wins 3Gemini 3 Pro Preview wins 14

Of the 17 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 Pro Preview? The short answer

Pick Gemini 3 Pro Preview: it scores higher (Intelligence Index 28.0 against 24.4) at about the same price.

  • Gemini 3 Pro Preview scores higher on the Artificial Analysis Intelligence Index: 28.0 against 24.4.
  • DeepSeek-V4-Flash (0423) is newer: released 24 Apr 2026, against 18 Nov 2025 for Gemini 3 Pro Preview.
  • On third-party benchmarks, on the results both models have: Gemini 3 Pro Preview does better for reasoning and knowledge, writing and sticking to the facts.

Head to head

24.4
Intelligence Index
28.0

Every fact side by side

DeepSeek-V4-Flash (0423)Gemini 3 Pro Preview
Price per million tokens$0.050 in · $0.45 outNot on sale
Blended (3 in : 1 out)$0.15–
Cheapest host, blended$0.10 (StreamLake, FP8)–
Intelligence Index24.428.0
Spring Prompt overall––
Output speed, tokens a second––
Context window1,048,576 tokens–
Released24 Apr 2026 (newer)18 Nov 2025
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.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 59 of 159 82 of 160
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 45 of 52
Reasoning and knowledgeHard questions across science, maths and general knowledge 69 of 187 51 of 188
WritingWhat people prefer in blind comparisons, and judged writing quality 63 of 169 21 of 170
Sticking to the factsSummarising without inventing things, and factual answers 81 of 139 62 of 140

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 Pro Preview
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 85 · 16 of 387 measured 1,438high reasoning 1,485
Overall · Text factualityArena rating, higher is better 81 · 11 of 163 measured 1,439 1,481
Business, management and finance · TextArena rating, higher is better 91 · 28 of 380 measured 1,439 1,474
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 85 · 63 of 249 measured 24.4high reasoning 28.0high reasoning
GPQA Diamond% of questions, higher is better 52 · 35 of 232 measured 89.4%max reasoning 90.8%high reasoning
Humanity's Last Exam% of questions, higher is better 67 · 48 of 250 measured 34.8%max reasoning 39.7%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 60 · 25 of 230 measured 54.6no reasoning 66.7high reasoning
Requested-length error · UGI% off the requested word count, lower is better 54 · 176 of 230 measured 12.0%thinking reasoning 33.0%low reasoning
Style adherence · UGIscore from 0 to 1, higher is better 55 · 49 of 230 measured 0.37thinking reasoning 0.37high reasoning
Show all 17 results (8 more)
MeasureDeepSeek-V4-Flash (0423)Gemini 3 Pro Preview
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 78 · 8 of 385 measured 1,410high reasoning 1,484
Expert prompts · TextArena rating, higher is better 83 · 39 of 338 measured 1,466high reasoning 1,498
Instruction following · TextArena rating, higher is better 79 · 26 of 387 measured 1,433high reasoning 1,473
Writing, literature and language · TextArena rating, higher is better 78 · 10 of 386 measured 1,422high reasoning 1,481
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 7 · 52 of 195 measured 79.2%max reasoning 70.4%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 89 · 80 of 241 measured 74.3%max reasoning 76.0%high reasoning
Terminal-Bench Hard% of tasks, higher is better 37 · 32 of 190 measured 38.6%high reasoning 41.7%high reasoning
τ²-bench telecom% of tasks, higher is better 16 · 49 of 193 measured 95.6%high reasoning 87.1%high reasoning

Quick answers

Is DeepSeek-V4-Flash (0423) better than Gemini 3 Pro Preview?

Pick Gemini 3 Pro Preview: it scores higher (Intelligence Index 28.0 against 24.4) at about the same price.

Which is better for agents and tool use, DeepSeek-V4-Flash (0423) or Gemini 3 Pro Preview?

DeepSeek-V4-Flash (0423) ranks 59 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 82 for Gemini 3 Pro Preview.

Which is better for reasoning and knowledge, DeepSeek-V4-Flash (0423) or Gemini 3 Pro Preview?

Gemini 3 Pro Preview ranks 51 of 187 models on sale for hard questions across science, maths and general knowledge, against 69 for DeepSeek-V4-Flash (0423).

Which is better for writing, DeepSeek-V4-Flash (0423) or Gemini 3 Pro Preview?

Gemini 3 Pro Preview ranks 21 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 Pro Preview?

Gemini 3 Pro Preview ranks 62 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 Pro Preview 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.