Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs Gemini 3.6 Flash

Gemini 3.6 Flash leads DeepSeek V4 Pro 0423 on coding, 62.5 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 1.3x less per output token ($2.976 vs $3.75 per million). Updated October 22, 2026; 75 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0423 Replace Gemini 3.6 Flash
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
50.0
Output $/M
$2.976
4
Gemini 3.6 FlashGoogle
Coding
62.5
Overall
68.3
Output $/M
$3.75
70
vs boards won of 75 shared, 1 tied

DeepSeek V4 Pro 0423 or Gemini 3.6 Flash: which to pick

Pick Gemini 3.6 Flash for coding: it scores 62.5 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 4 benchmarks against 5.

Pick DeepSeek V4 Pro 0423 for output tokens 1.3x cheaper ($2.976 vs $3.75 per million) and a lower cost per solved task ($0.57 against $1.49).

Model ADeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved taskModel BGemini 3.6 FlashGoogle62.5/1004 independent benchmarks$1.49 per solved task
Shared results
75
DeepSeek V4 Pro 0423 only
9
Gemini 3.6 Flash only
34
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
DeepSeek V4 Pro 0423 38.7 from 5 benchmarks, Gemini 3.6 Flash 62.5 from 4 benchmarks.
Widest category
Agentic work, 13.1 points apart on average over 7 shared benchmarks.
Widest single gap
Design Arena: agents building full-stack apps: DeepSeek V4 Pro 0423 948 against Gemini 3.6 Flash 1181, 29.1 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $2.976 against Gemini 3.6 Flash $3.75 per million output tokens, 1.3x apart.
Context window
Both take 1.05M tokens.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryDeepSeek V4 Pro 0423BarsGemini 3.6 FlashTies
Coding1131 tie
Intelligence02
Agentic work16
Reasoning07
Math15
Knowledge010
Web design07
General120
All shared boards4701 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index113
Coding benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
LMArena WebDev14471538Gemini 3.6 Flash
AA Coding Index59.469.2Gemini 3.6 Flash
LiveCodeBench (Vals AI)87.5%88.1%Gemini 3.6 Flash
SWE-bench Verified (Vals AI)77.4%79.6%Gemini 3.6 Flash
Terminal-Bench 4 (Vals AI)11.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Vibe Code Bench (Vals AI)49.9%64.0%Gemini 3.6 Flash
Code migration (Vals AI)26.2%30.9%Gemini 3.6 Flash
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)Not measured35.1%Only Gemini 3.6 Flash measured
Terminal-Bench 2.1 (Vals AI)50.2%73.8%Gemini 3.6 Flash
SkillsBench (Vals AI)51.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
CyberBench (Vals AI)Not measured45.4%Only Gemini 3.6 Flash measured
SciCodeNot measured53.4%Only Gemini 3.6 Flash measured
FrontierCode17.6%34.4%Gemini 3.6 Flash
WeirdML48.9%56.1%Gemini 3.6 Flash
ALE-Bench1006.1715.5DeepSeek V4 Pro 0423
LMArena Text: coding14701491Gemini 3.6 Flash
LMArena Text: software and IT14691492Gemini 3.6 Flash
LMArena WebDev: React14411528Gemini 3.6 Flash
LMArena WebDev: HTML14351547Gemini 3.6 Flash
LMArena WebDev: from an imageNot measured1545Only Gemini 3.6 Flash measured
SciCodeNot measured10.8%Only Gemini 3.6 Flash measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
AA Intelligence Index30.434.0Gemini 3.6 Flash
Epoch Capabilities Index149.1154.5Gemini 3.6 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index16
Agentic work benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
AA Agentic Index26.329.0Gemini 3.6 Flash
Design Arena: agents building web apps10001197Gemini 3.6 Flash
Design Arena: agents building full-stack apps9481181Gemini 3.6 Flash
Design Arena: agents building mobile appsNot measured1198Only Gemini 3.6 Flash measured
Design Arena: agents building Android appsNot measured1204Only Gemini 3.6 Flash measured
Design Arena: agents building Godot games1059Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building gamesNot measured1180Only Gemini 3.6 Flash measured
Design Arena: HTML slidesNot measured1099Only Gemini 3.6 Flash measured
Design Arena: PowerPoint slidesNot measured1121Only Gemini 3.6 Flash measured
Design Arena: spreadsheetsNot measured1071Only Gemini 3.6 Flash measured
Finance Agent (Vals AI)44.1%56.3%Gemini 3.6 Flash
Tax Agent Bench (Vals AI)25.2%18.0%DeepSeek V4 Pro 0423
Legal Research Bench (Vals AI)23.1%25.0%Gemini 3.6 Flash
Excel Modeling Benchmark (Vals AI)51.6%65.4%Gemini 3.6 Flash
BioMysteryBench (Vals AI)Not measured58.5%Only Gemini 3.6 Flash measured
Terminal-Bench-Science (Vals AI)Not measured4.3%Only Gemini 3.6 Flash measured
APEX-AgentsNot measured46.9%Only Gemini 3.6 Flash measured
Vending-Bench 2$3,285Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 23 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
GPQA Diamond89.4%93.4%Gemini 3.6 Flash
MMMU Pro (Vals AI)Not measured88.4%Only Gemini 3.6 Flash measured
GPQA Diamond (Artificial Analysis run)Not measured92.8%Only Gemini 3.6 Flash measured
Humanity's Last Exam (Artificial Analysis run)Not measured40.8%Only Gemini 3.6 Flash measured
GPQA Diamond (Epoch AI run)90.9%94.1%Gemini 3.6 Flash
ARC-AGINot measured91.2%Only Gemini 3.6 Flash measured
ARC-AGI-2Not measured60.4%Only Gemini 3.6 Flash measured
Chess puzzles19.0%42.0%Gemini 3.6 Flash
Mystery game puzzles17.0%30.0%Gemini 3.6 Flash
LMArena Text: hard prompts14611486Gemini 3.6 Flash
LMArena Text: expert14631490Gemini 3.6 Flash
LMArena Text: hard prompts in English14661484Gemini 3.6 Flash
LMArena Vision: diagramsNot measured1314Only Gemini 3.6 Flash measured
LMArena Vision: homeworkNot measured1314Only Gemini 3.6 Flash measured
Kagi LLM Benchmark53.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index15
Math benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
OTIS Mock AIME96.7%94.2%DeepSeek V4 Pro 0423
FrontierMath, tiers 1 to 345.3%58.9%Gemini 3.6 Flash
FrontierMath, tier 42.4%22.0%Gemini 3.6 Flash
ProofBench16.0%36.0%Gemini 3.6 Flash
LMArena Text: math14431508Gemini 3.6 Flash
LMArena Text: mathematical work14551492Gemini 3.6 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index010
Knowledge benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
MMLU Pro87.3%89.3%Gemini 3.6 Flash
LegalBench (Vals AI)80.3%86.7%Gemini 3.6 Flash
CaseLaw (Vals AI)59.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)61.4%63.3%Gemini 3.6 Flash
TaxEval (Vals AI)72.1%74.9%Gemini 3.6 Flash
MortgageTax (Vals AI)Not measured67.6%Only Gemini 3.6 Flash measured
MedCode (Vals AI)40.5%53.1%Gemini 3.6 Flash
SimpleQA Verified47.0%66.2%Gemini 3.6 Flash
LMArena Text: science14701489Gemini 3.6 Flash
LMArena Text: medicine and healthcare14661469Gemini 3.6 Flash
LMArena Text: legal and government14641479Gemini 3.6 Flash
LMArena Text: business and finance14431464Gemini 3.6 Flash
FACTS Benchmark SuiteNot measured65.3%Only Gemini 3.6 Flash measured
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
Design Arena: websites12341300Gemini 3.6 Flash
Design Arena: UI components12191294Gemini 3.6 Flash
Design Arena: game dev12281263Gemini 3.6 Flash
Design Arena: data viz12031289Gemini 3.6 Flash
Design Arena: 3D12531271Gemini 3.6 Flash
Design Arena: all code categories12401289Gemini 3.6 Flash
Design Arena: SVG1139Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: ASCII art11491281Gemini 3.6 Flash
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index120
General benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
Public Benefits Bench (Vals AI)62.9%56.6%DeepSeek V4 Pro 0423
SAGE (Vals AI)Not measured48.7%Only Gemini 3.6 Flash measured
MedScribe (Vals AI)75.1%79.7%Gemini 3.6 Flash
Vals Multimodal IndexNot measured65.1%Only Gemini 3.6 Flash measured
Long context reasoning (AA-LCR)Not measured80.0%Only Gemini 3.6 Flash measured
DTBench90.7%95.5%Gemini 3.6 Flash
LMCA41.2%44.9%Gemini 3.6 Flash
Surface Evolver Bench40.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
Furniture assemblyNot measured23.3%Only Gemini 3.6 Flash measured
CL-bench Life13.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text14511480Gemini 3.6 Flash
LMArena Text: instruction following14451467Gemini 3.6 Flash
LMArena Text: creative writing14461466Gemini 3.6 Flash
LMArena VisionNot measured1299Only Gemini 3.6 Flash measured
LMArena Text: English14591482Gemini 3.6 Flash
LMArena Text: non-English14391470Gemini 3.6 Flash
LMArena Text: Chinese14811531Gemini 3.6 Flash
LMArena Text: German14581480Gemini 3.6 Flash
LMArena Text: Japanese14461475Gemini 3.6 Flash
LMArena Text: Korean14091429Gemini 3.6 Flash
LMArena Text: French14731503Gemini 3.6 Flash
LMArena Text: Spanish14571476Gemini 3.6 Flash
LMArena Text: Russian14531488Gemini 3.6 Flash
LMArena Text: Polish14611473Gemini 3.6 Flash
LMArena Text: multi-turn14681481Gemini 3.6 Flash
LMArena Text: longer queries14581475Gemini 3.6 Flash
LMArena Text: writing and language14471470Gemini 3.6 Flash
LMArena Text: entertainment and media14311456Gemini 3.6 Flash
LMArena Vision: EnglishNot measured1295Only Gemini 3.6 Flash measured
LMArena Vision: ChineseNot measured1357Only Gemini 3.6 Flash measured
LMArena Vision: reading textNot measured1312Only Gemini 3.6 Flash measured
LMArena Vision: humorNot measured1289Only Gemini 3.6 Flash measured
LMArena Vision: creative writingNot measured1278Only Gemini 3.6 Flash measured
LMArena DocumentNot measured1456Only Gemini 3.6 Flash measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
BenchmarkDeepSeek V4 Pro 0423Gemini 3.6 FlashLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

DeepSeek V4 Pro 0423$0.0028Fits in one request
Gemini 3.6 Flash$0.0026Fits in one request

Gemini 3.6 Flash costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.077Fits in one request
Gemini 3.6 Flash$0.049Fits in one request

Gemini 3.6 Flash costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.301Fits in one request
Gemini 3.6 Flash$0.188Fits in one request

Gemini 3.6 Flash costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of DeepSeek V4 Pro 0423 and Gemini 3.6 Flash
SpecificationDeepSeek V4 Pro 0423Google Gemini 3.6 Flash
MakerDeepSeekGoogle
WeightsOpen weightsNo public weights listed
ReleasedApril 24, 2026July 21, 2026
Context window1.05M1.05M
Input $/Mtok$1.358$0.75
Output $/Mtok$2.976$3.75
Coding index38.762.5
Independent measurements behind it54
Cost per solved task$0.57$1.49
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than Gemini 3.6 Flash for coding?

Pick Gemini 3.6 Flash for coding: it scores 62.5 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 4 benchmarks against 5. Pick DeepSeek V4 Pro 0423 for output tokens 1.3x cheaper ($2.976 vs $3.75 per million) and a lower cost per solved task ($0.57 against $1.49).

Which is cheaper, DeepSeek V4 Pro 0423 or Gemini 3.6 Flash?

DeepSeek V4 Pro 0423 costs $1.358 per million input tokens and $2.976 per million output tokens; Gemini 3.6 Flash costs $0.75 and $3.75. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and Gemini 3.6 Flash $1.49.

Which has the bigger context window, DeepSeek V4 Pro 0423 or Gemini 3.6 Flash?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0423 vs Gemini 3.6 Flash comparison based on?

75 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 independent benchmarks and Gemini 3.6 Flash's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/deepseek-v4-pro-vs-gemini-3-6-flash" title="DeepSeek V4 Pro 0423 vs Gemini 3.6 Flash, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/deepseek-v4-pro-vs-gemini-3-6-flash">LLMBenchmark.ai, DeepSeek V4 Pro 0423 vs Gemini 3.6 Flash</a></p>