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

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

Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 3 sources that measured both models.

DeepSeekDeepSeek-V4-Flash (0423) Released 24 Apr 2026 · $0.050 in · $0.45 out
GoogleGemini 3 Flash Preview Released 17 Dec 2025 · $0.50 in · $3.00 out
DeepSeek-V4-Flash (0423) wins 41 too close to callGemini 3 Flash Preview wins 13

Of the 18 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 Flash Preview? The short answer

They score about the same, so pick DeepSeek-V4-Flash (0423): it costs 7.5 times less per token.

  • DeepSeek-V4-Flash (0423) is cheaper: $0.15 against $1.12 per million tokens, 7.5 times less.
  • Gemini 3 Flash Preview scores higher on the Artificial Analysis Intelligence Index: 26.3 against 24.4.
  • DeepSeek-V4-Flash (0423) is newer: released 24 Apr 2026, against 17 Dec 2025 for Gemini 3 Flash Preview.
  • On third-party benchmarks, on the results both models have: DeepSeek-V4-Flash (0423) does better for agents and tool use; Gemini 3 Flash Preview for reasoning and knowledge, writing and sticking to the facts.

Head to head

24.4
Intelligence Index
26.3
$0.15
Price per million tokens, blendedlower is better
$1.12
1,048,576
Context window, tokens
1,048,576

Every fact side by side

DeepSeek-V4-Flash (0423)Gemini 3 Flash Preview
Price per million tokens$0.050 in · $0.45 out$0.50 in · $3.00 out
Blended (3 in : 1 out)$0.15$1.12
Cheapest host, blended$0.10 (StreamLake, FP8)$1.12 (Google)
Intelligence Index24.426.3
Spring Prompt overall––
Output speed, tokens a second––
Context window1,048,576 tokens1,048,576 tokens
Released24 Apr 2026 (newer)17 Dec 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 85 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 60 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 63 of 169 28 of 169
Sticking to the factsSummarising without inventing things, and factual answers 81 of 139 53 of 139

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 Flash Preview
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 85 · 36 of 387 measured 1,438high reasoning 1,473
Overall · Text factualityArena rating, higher is better 81 · 27 of 163 measured 1,439 1,468
Business, management and finance · TextArena rating, higher is better 91 · 34 of 380 measured 1,439 1,468
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 85 · 71 of 249 measured 24.4high reasoning 26.3thinking reasoning
GPQA Diamond% of questions, higher is better 52 · 44 of 232 measured 89.4%max reasoning 89.8%thinking reasoning
Humanity's Last Exam% of questions, higher is better 67 · 60 of 250 measured 34.8%max reasoning 36.6%thinking reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 60 · 18 of 230 measured 54.6no reasoning 67.7medium reasoning
Requested-length error · UGI% off the requested word count, lower is better 54 · 76 of 230 measured 12.0%thinking reasoning 16.0%minimal reasoning
Style adherence · UGIscore from 0 to 1, higher is better 55 · 52 of 230 measured 0.37thinking reasoning 0.37high reasoning
Show all 18 results (9 more)
MeasureDeepSeek-V4-Flash (0423)Gemini 3 Flash Preview
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 78 · 23 of 385 measured 1,410high reasoning 1,457
Expert prompts · TextArena rating, higher is better 83 · 44 of 338 measured 1,466high reasoning 1,496
Instruction following · TextArena rating, higher is better 79 · 44 of 387 measured 1,433high reasoning 1,457
Writing, literature and language · TextArena rating, higher is better 78 · 28 of 386 measured 1,422high reasoning 1,461
Artificial Analysis reported by Artificial Analysis · 5 results
τ-bench banking% of tasks, higher is better 34 · 48 of 121 measured 30.9%max reasoning 20.8%thinking reasoning
IFBench% of instructions, higher is better 7 · 9 of 195 measured 79.2%max reasoning 78.0%thinking reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 89 · 65 of 241 measured 74.3%max reasoning 78.0%thinking reasoning
Terminal-Bench Hard% of tasks, higher is better 37 · 37 of 190 measured 38.6%high reasoning 38.6%thinking reasoning
τ²-bench telecom% of tasks, higher is better 16 · 70 of 193 measured 95.6%high reasoning 80.4%thinking reasoning

Quick answers

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

They score about the same, so pick DeepSeek-V4-Flash (0423): it costs 7.5 times less per token.

Which is cheaper, DeepSeek-V4-Flash (0423) or Gemini 3 Flash Preview?

DeepSeek-V4-Flash (0423) is cheaper: $0.15 against $1.12 per million tokens, 7.5 times less.

Which is better for agents and tool use, DeepSeek-V4-Flash (0423) or Gemini 3 Flash 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 85 for Gemini 3 Flash Preview.

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

Gemini 3 Flash Preview ranks 60 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 Flash Preview?

Gemini 3 Flash Preview ranks 28 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 Flash Preview?

Gemini 3 Flash Preview ranks 53 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 Flash 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.