Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0423 vs Gemini 3.8 Flash

Gemini 3.8 Flash leads DeepSeek V4 Flash 0423 on the Artificial Analysis Intelligence Index, 40.9 to 24.4, and DeepSeek V4 Flash 0423 costs 13.4x less per output token ($0.28 vs $3.75 per million). Updated October 21, 2026; 47 benchmarks have a result for both.

Replace DeepSeek V4 Flash 0423 Replace Gemini 3.8 Flash
DeepSeek V4 Flash 0423DeepSeek
Coding
No data
Overall
No data
Output $/M
$0.28
1
Gemini 3.8 FlashGoogle
Coding
61.6
Overall
69.0
Output $/M
$3.75
46
vs boards won of 47 shared

DeepSeek V4 Flash 0423 or Gemini 3.8 Flash: which to pick

Only Gemini 3.8 Flash has a coding score, 61.6 on the Vibe Coding Index; DeepSeek V4 Flash 0423 has none, so the two cannot be ranked on coding.

Pick DeepSeek V4 Flash 0423 for output tokens 13.4x cheaper ($0.28 vs $3.75 per million) and work measured by LMArena WebDev: React, where it leads.

Model ADeepSeek V4 Flash 0423DeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel BGemini 3.8 FlashGoogle61.6/1006 independent benchmarks$2.74 per solved task
Shared results
47
DeepSeek V4 Flash 0423 only
2
Gemini 3.8 Flash only
81
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 Flash 0423 not benchmarked, Gemini 3.8 Flash 61.6 from 6 benchmarks.
Widest category
Math, 16.1 points apart on average over 2 shared benchmarks.
Widest single gap
WeirdML: DeepSeek V4 Flash 0423 45.6% against Gemini 3.8 Flash 84.8%, 39.2 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0423 $0.28 against Gemini 3.8 Flash $3.75 per million output tokens, 13.4x 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 Flash 0423BarsGemini 3.8 FlashTies
Coding17
Intelligence02
Agentic work01
Reasoning03
Math02
Knowledge04
Web design08
General019
All shared boards146
CodingLike-for-likeSix of these boards feed the Vibe Coding Index17
Coding benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 FlashLeader
LiveBench codingNot measured82.2%Only Gemini 3.8 Flash measured
LMArena WebDev15821585Gemini 3.8 Flash
AA Coding Index52.076.3Gemini 3.8 Flash
LiveCodeBench (Vals AI)Not measured89.5%Only Gemini 3.8 Flash measured
SWE-bench Verified (Vals AI)Not measured80.0%Only Gemini 3.8 Flash measured
Terminal-Bench 4 (Vals AI)Not measured19.7%Only Gemini 3.8 Flash measured
Vibe Code Bench (Vals AI)Not measured78.7%Only Gemini 3.8 Flash measured
Code migration (Vals AI)Not measured36.5%Only Gemini 3.8 Flash measured
ProgramBench (Vals AI)Not measured1.0%Only Gemini 3.8 Flash measured
IOI (Vals AI)Not measured56.9%Only Gemini 3.8 Flash measured
Terminal-Bench 2.1 (Vals AI)Not measured81.3%Only Gemini 3.8 Flash measured
SWE-bench Multimodal (Vals AI)Not measured40.8%Only Gemini 3.8 Flash measured
Vibe Code Bench 1-100 (Vals AI)Not measured18.8%Only Gemini 3.8 Flash measured
SkillsBench (Vals AI)Not measured58.0%Only Gemini 3.8 Flash measured
CyberBench (Vals AI)Not measured43.8%Only Gemini 3.8 Flash measured
SciCodeNot measured56.6%Only Gemini 3.8 Flash measured
FrontierCodeNot measured41.2%Only Gemini 3.8 Flash measured
FrontierSWENot measured19.6%Only Gemini 3.8 Flash measured
WeirdML45.6%84.8%Gemini 3.8 Flash
ALE-Bench678.21269.7Gemini 3.8 Flash
LMArena Text: coding14571508Gemini 3.8 Flash
LMArena Text: software and IT14531507Gemini 3.8 Flash
LMArena WebDev: React15851577DeepSeek V4 Flash 0423
LMArena WebDev: HTML15581616Gemini 3.8 Flash
LMArena WebDev: from an imageNot measured1593Only Gemini 3.8 Flash measured
SciCodeNot measured12.3%Only Gemini 3.8 Flash measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 FlashLeader
AA Intelligence Index24.440.9Gemini 3.8 Flash
Epoch Capabilities Index146.1157.4Gemini 3.8 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 FlashLeader
AA Agentic Index26.340.2Gemini 3.8 Flash
Design Arena: agents building web appsNot measured1238Only Gemini 3.8 Flash measured
Design Arena: agents building full-stack appsNot measured1244Only Gemini 3.8 Flash measured
Design Arena: agents building mobile appsNot measured1236Only Gemini 3.8 Flash measured
Design Arena: agents building Android appsNot measured1074Only Gemini 3.8 Flash measured
Design Arena: agents building Godot gamesNot measured1273Only Gemini 3.8 Flash measured
Design Arena: PowerPoint slidesNot measured1177Only Gemini 3.8 Flash measured
Design Arena: spreadsheetsNot measured1056Only Gemini 3.8 Flash measured
LiveBench researchNot measured79.1%Only Gemini 3.8 Flash measured
LiveBench browserNot measured64.0%Only Gemini 3.8 Flash measured
LiveBench long agenticNot measured30.1%Only Gemini 3.8 Flash measured
SREBench (Vals AI)Not measured11.1%Only Gemini 3.8 Flash measured
Finance Agent (Vals AI)Not measured61.4%Only Gemini 3.8 Flash measured
Tax Agent Bench (Vals AI)Not measured32.1%Only Gemini 3.8 Flash measured
Legal Research Bench (Vals AI)Not measured38.9%Only Gemini 3.8 Flash measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.1%Only Gemini 3.8 Flash measured
Excel Modeling Benchmark (Vals AI)Not measured72.2%Only Gemini 3.8 Flash measured
BioMysteryBench (Vals AI)Not measured62.2%Only Gemini 3.8 Flash measured
Terminal-Bench-Science (Vals AI)Not measured8.6%Only Gemini 3.8 Flash measured
Vals Science IndexNot measured35.8%Only Gemini 3.8 Flash measured
Time Horizon Index (Vals AI)Not measured18.8%Only Gemini 3.8 Flash measured
CUA-bench (Vals AI)Not measured4.2%Only Gemini 3.8 Flash measured
APEX-AgentsNot measured64.3%Only Gemini 3.8 Flash measured
Remote Labor IndexNot measured5.8%Only Gemini 3.8 Flash measured
Vending-Bench 2Not measured$5,094Only Gemini 3.8 Flash measured
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 FlashLeader
GPQA DiamondNot measured94.4%Only Gemini 3.8 Flash measured
LiveBench reasoningNot measured89.3%Only Gemini 3.8 Flash measured
MysteryMechanism (Vals AI)Not measured36.5%Only Gemini 3.8 Flash measured
MMMU Pro (Vals AI)Not measured89.1%Only Gemini 3.8 Flash measured
GPQA Diamond (Artificial Analysis run)Not measured95.3%Only Gemini 3.8 Flash measured
Humanity's Last Exam (Artificial Analysis run)Not measured47.8%Only Gemini 3.8 Flash measured
GPQA Diamond (Epoch AI run)Not measured95.4%Only Gemini 3.8 Flash measured
ARC-AGINot measured98.5%Only Gemini 3.8 Flash measured
ARC-AGI-2Not measured89.2%Only Gemini 3.8 Flash measured
SimpleBench46.3%Not measuredOnly DeepSeek V4 Flash 0423 measured
Chess puzzlesNot measured58.0%Only Gemini 3.8 Flash measured
Mystery game puzzlesNot measured47.0%Only Gemini 3.8 Flash measured
LMArena Text: hard prompts14441509Gemini 3.8 Flash
LMArena Text: expert14411526Gemini 3.8 Flash
LMArena Text: hard prompts in English14491504Gemini 3.8 Flash
LMArena Vision: diagramsNot measured1345Only Gemini 3.8 Flash measured
LMArena Vision: homeworkNot measured1351Only Gemini 3.8 Flash measured
Kagi LLM Benchmark52.2%Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 FlashLeader
OTIS Mock AIMENot measured98.9%Only Gemini 3.8 Flash measured
FrontierMath, tiers 1 to 3Not measured68.4%Only Gemini 3.8 Flash measured
FrontierMath, tier 4Not measured22.0%Only Gemini 3.8 Flash measured
ProofBenchNot measured48.0%Only Gemini 3.8 Flash measured
LMArena Text: math14261532Gemini 3.8 Flash
LMArena Text: mathematical work14321519Gemini 3.8 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 FlashLeader
MMLU ProNot measured90.2%Only Gemini 3.8 Flash measured
LegalBench (Vals AI)Not measured87.0%Only Gemini 3.8 Flash measured
TaxEval (Vals AI)Not measured74.5%Only Gemini 3.8 Flash measured
MortgageTax (Vals AI)Not measured65.3%Only Gemini 3.8 Flash measured
MedCode (Vals AI)Not measured48.1%Only Gemini 3.8 Flash measured
SimpleQA VerifiedNot measured69.7%Only Gemini 3.8 Flash measured
LMArena Text: science14461523Gemini 3.8 Flash
LMArena Text: medicine and healthcare14481508Gemini 3.8 Flash
LMArena Text: legal and government14391497Gemini 3.8 Flash
LMArena Text: business and finance14251479Gemini 3.8 Flash
FACTS Benchmark SuiteNot measured69.4%Only Gemini 3.8 Flash measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 FlashLeader
Design Arena: websites12081300Gemini 3.8 Flash
Design Arena: UI components11651319Gemini 3.8 Flash
Design Arena: game dev11971305Gemini 3.8 Flash
Design Arena: data viz11271269Gemini 3.8 Flash
Design Arena: 3D11891295Gemini 3.8 Flash
Design Arena: all code categories12051304Gemini 3.8 Flash
Design Arena: SVG11551295Gemini 3.8 Flash
Design Arena: ASCII art11091265Gemini 3.8 Flash
LiveBench designNot measured72.7%Only Gemini 3.8 Flash measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
General benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 FlashLeader
Vals IndexNot measured56.0%Only Gemini 3.8 Flash measured
LiveBench data analysisNot measured54.0%Only Gemini 3.8 Flash measured
Public Benefits Bench (Vals AI)Not measured65.3%Only Gemini 3.8 Flash measured
SAGE (Vals AI)Not measured35.1%Only Gemini 3.8 Flash measured
MedScribe (Vals AI)Not measured84.5%Only Gemini 3.8 Flash measured
Long context reasoning (AA-LCR)Not measured84.0%Only Gemini 3.8 Flash measured
DTBench86.4%95.7%Gemini 3.8 Flash
LMCA35.9%52.9%Gemini 3.8 Flash
Surface Evolver BenchNot measured76.9%Only Gemini 3.8 Flash measured
Furniture assemblyNot measured31.7%Only Gemini 3.8 Flash measured
LMArena Text14321499Gemini 3.8 Flash
LMArena Text: instruction following14211492Gemini 3.8 Flash
LMArena Text: creative writing14031488Gemini 3.8 Flash
LMArena VisionNot measured1315Only Gemini 3.8 Flash measured
LMArena Text: English14411498Gemini 3.8 Flash
LMArena Text: non-English14191491Gemini 3.8 Flash
LMArena Text: Chinese14631553Gemini 3.8 Flash
LMArena Text: German14191501Gemini 3.8 Flash
LMArena Text: Japanese13891507Gemini 3.8 Flash
LMArena Text: Korean13831464Gemini 3.8 Flash
LMArena Text: French14391496Gemini 3.8 Flash
LMArena Text: Spanish14361487Gemini 3.8 Flash
LMArena Text: Russian14271514Gemini 3.8 Flash
LMArena Text: Polish14361497Gemini 3.8 Flash
LMArena Text: multi-turn14491503Gemini 3.8 Flash
LMArena Text: longer queries14341507Gemini 3.8 Flash
LMArena Text: writing and language14101494Gemini 3.8 Flash
LMArena Text: entertainment and media14001480Gemini 3.8 Flash
LMArena Vision: EnglishNot measured1318Only Gemini 3.8 Flash measured
LMArena Vision: ChineseNot measured1416Only Gemini 3.8 Flash measured
LMArena Vision: reading textNot measured1333Only Gemini 3.8 Flash measured
LMArena Vision: humorNot measured1321Only Gemini 3.8 Flash measured
LMArena Vision: creative writingNot measured1299Only Gemini 3.8 Flash measured
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Flash 0423 and Gemini 3.8 Flash
BenchmarkDeepSeek V4 Flash 0423Gemini 3.8 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 Flash 0423$0.0003Fits in one request
Gemini 3.8 Flash$0.0026Fits in one request

DeepSeek V4 Flash 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Flash 0423$0.0073Fits in one request
Gemini 3.8 Flash$0.049Fits in one request

DeepSeek V4 Flash 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0423$0.029Fits in one request
Gemini 3.8 Flash$0.188Fits in one request

DeepSeek V4 Flash 0423 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 Flash 0423 and Gemini 3.8 Flash
SpecificationDeepSeek V4 Flash 0423Google Gemini 3.8 Flash
MakerDeepSeekGoogle
WeightsOpen weightsNo public weights listed
ReleasedApril 24, 2026September 2, 2026
Context window1.05M1.05M
Input $/Mtok$0.13$0.75
Output $/Mtok$0.28$3.75
Coding indexNot benchmarked61.6
Independent measurements behind it16
Cost per solved taskNot computable$2.74
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Flash 0423 better than Gemini 3.8 Flash for coding?

Only Gemini 3.8 Flash has a coding score, 61.6 on the Vibe Coding Index; DeepSeek V4 Flash 0423 has none, so the two cannot be ranked on coding. Pick DeepSeek V4 Flash 0423 for output tokens 13.4x cheaper ($0.28 vs $3.75 per million) and work measured by LMArena WebDev: React, where it leads.

Which is cheaper, DeepSeek V4 Flash 0423 or Gemini 3.8 Flash?

DeepSeek V4 Flash 0423 costs $0.13 per million input tokens and $0.28 per million output tokens; Gemini 3.8 Flash costs $0.75 and $3.75. Cost per solved task is known for Gemini 3.8 Flash only.

Which has the bigger context window, DeepSeek V4 Flash 0423 or Gemini 3.8 Flash?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Flash 0423 vs Gemini 3.8 Flash comparison based on?

47 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Flash 0423's coding index rests on 1 independent benchmark and Gemini 3.8 Flash's on 6. Where only one model has a result, the page says so instead of naming a winner.

Compare next