Enter opens the highlighted result. Esc closes.

DeepSeek V4.1 Flash vs Gemini 3.8 Flash

DeepSeek V4.1 Flash leads Gemini 3.8 Flash on coding, 62.5 to 61.6 on the Vibe Coding Index, and DeepSeek V4.1 Flash costs 4.5x less per output token ($0.84 vs $3.75 per million). Updated October 22, 2026; 101 benchmarks have a result for both.

Replace DeepSeek V4.1 Flash Replace Gemini 3.8 Flash
DeepSeek V4.1 FlashDeepSeek
Coding
62.5
Overall
62.4
Output $/M
$0.84
28
Gemini 3.8 FlashGoogle
Coding
61.6
Overall
69.0
Output $/M
$3.75
71
vs boards won of 101 shared, 2 tied

DeepSeek V4.1 Flash or Gemini 3.8 Flash: which to pick

DeepSeek V4.1 Flash and Gemini 3.8 Flash are level for coding, 62.5 against 61.6 on the Vibe Coding Index, so price and context decide.

Pick Gemini 3.8 Flash for work measured by ProgramBench (Vals AI) or IOI (Vals AI), where it leads. Pick DeepSeek V4.1 Flash for output tokens 4.5x cheaper ($0.84 vs $3.75 per million) and work measured by LiveBench coding or LMArena WebDev, where it leads.

Model ADeepSeek V4.1 FlashDeepSeek62.5/1005 independent benchmarksNo cost per solved taskModel BGemini 3.8 FlashGoogle61.6/1006 independent benchmarks$2.74 per solved task
Shared results
101
DeepSeek V4.1 Flash only
0
Gemini 3.8 Flash only
27
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 V4.1 Flash 62.5 from 5 benchmarks, Gemini 3.8 Flash 61.6 from 6 benchmarks.
Widest category
Agentic work, 10.3 points apart on average over 12 shared benchmarks.
Widest single gap
Surface Evolver Bench: DeepSeek V4.1 Flash 46.3% against Gemini 3.8 Flash 76.9%, 30.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V4.1 Flash $0.84 against Gemini 3.8 Flash $3.75 per million output tokens, 4.5x 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 V4.1 FlashBarsGemini 3.8 FlashTies
Coding1091 tie
Intelligence02
Agentic work57
Reasoning013
Math24
Knowledge07
Web design72
General4271 tie
All shared boards28712 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index109
Coding benchmarks for DeepSeek V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 3.8 FlashLeader
LiveBench coding90.2%82.2%DeepSeek V4.1 Flash
LMArena WebDev16181585DeepSeek V4.1 Flash
AA Coding IndexNot measured76.3Only Gemini 3.8 Flash measured
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)19.7%19.7%Tie
Vibe Code Bench (Vals AI)84.7%78.7%DeepSeek V4.1 Flash
Code migration (Vals AI)45.6%36.5%DeepSeek V4.1 Flash
ProgramBench (Vals AI)0.5%1.0%Gemini 3.8 Flash
IOI (Vals AI)40.3%56.9%Gemini 3.8 Flash
Terminal-Bench 2.1 (Vals AI)74.5%81.3%Gemini 3.8 Flash
SWE-bench Multimodal (Vals AI)46.5%40.8%DeepSeek V4.1 Flash
Vibe Code Bench 1-100 (Vals AI)16.4%18.8%Gemini 3.8 Flash
SkillsBench (Vals AI)69.8%58.0%DeepSeek V4.1 Flash
CyberBench (Vals AI)73.7%43.8%DeepSeek V4.1 Flash
SciCode51.9%56.6%Gemini 3.8 Flash
FrontierCode43.9%41.2%DeepSeek V4.1 Flash
FrontierSWENot measured19.6%Only Gemini 3.8 Flash measured
WeirdMLNot measured84.8%Only Gemini 3.8 Flash measured
ALE-Bench1092.31269.7Gemini 3.8 Flash
LMArena Text: coding15021508Gemini 3.8 Flash
LMArena Text: software and IT14961507Gemini 3.8 Flash
LMArena WebDev: React16281577DeepSeek V4.1 Flash
LMArena WebDev: HTML16121616Gemini 3.8 Flash
LMArena WebDev: from an image16061593DeepSeek V4.1 Flash
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 V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 3.8 FlashLeader
AA Intelligence Index24.740.9Gemini 3.8 Flash
Epoch Capabilities Index155.9157.4Gemini 3.8 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index57
Agentic work benchmarks for DeepSeek V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 3.8 FlashLeader
AA Agentic IndexNot measured40.2Only Gemini 3.8 Flash measured
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 measured1078Only Gemini 3.8 Flash measured
Design Arena: agents building Godot gamesNot measured1273Only Gemini 3.8 Flash measured
Design Arena: PowerPoint slidesNot measured1153Only Gemini 3.8 Flash measured
Design Arena: spreadsheetsNot measured1022Only Gemini 3.8 Flash measured
LiveBench research86.8%79.1%DeepSeek V4.1 Flash
LiveBench browser84.0%64.0%DeepSeek V4.1 Flash
LiveBench long agentic40.1%30.1%DeepSeek V4.1 Flash
SREBench (Vals AI)0.8%11.1%Gemini 3.8 Flash
Finance Agent (Vals AI)53.5%61.4%Gemini 3.8 Flash
Tax Agent Bench (Vals AI)26.6%32.1%Gemini 3.8 Flash
Legal Research Bench (Vals AI)41.4%38.9%DeepSeek V4.1 Flash
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.1%Only Gemini 3.8 Flash measured
Excel Modeling Benchmark (Vals AI)57.2%72.2%Gemini 3.8 Flash
BioMysteryBench (Vals AI)67.8%62.2%DeepSeek V4.1 Flash
Terminal-Bench-Science (Vals AI)0.0%8.6%Gemini 3.8 Flash
Vals Science Index29.6%35.8%Gemini 3.8 Flash
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-Agents39.5%64.3%Gemini 3.8 Flash
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 index013
Reasoning benchmarks for DeepSeek V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 3.8 FlashLeader
GPQA DiamondNot measured94.4%Only Gemini 3.8 Flash measured
LiveBench reasoning86.7%89.3%Gemini 3.8 Flash
MysteryMechanism (Vals AI)21.2%36.5%Gemini 3.8 Flash
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)39.2%47.8%Gemini 3.8 Flash
GPQA Diamond (Epoch AI run)89.8%95.4%Gemini 3.8 Flash
ARC-AGI94.5%98.5%Gemini 3.8 Flash
ARC-AGI-272.9%89.2%Gemini 3.8 Flash
Chess puzzles48.0%58.0%Gemini 3.8 Flash
Mystery game puzzles43.0%47.0%Gemini 3.8 Flash
LMArena Text: hard prompts14831509Gemini 3.8 Flash
LMArena Text: expert15011526Gemini 3.8 Flash
LMArena Text: hard prompts in English14881504Gemini 3.8 Flash
LMArena Vision: diagrams12971345Gemini 3.8 Flash
LMArena Vision: homework13071351Gemini 3.8 Flash
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for DeepSeek V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 3.8 FlashLeader
OTIS Mock AIME98.3%98.9%Gemini 3.8 Flash
FrontierMath, tiers 1 to 367.4%68.4%Gemini 3.8 Flash
FrontierMath, tier 426.8%22.0%DeepSeek V4.1 Flash
ProofBench54.0%48.0%DeepSeek V4.1 Flash
LMArena Text: math14781532Gemini 3.8 Flash
LMArena Text: mathematical work14851519Gemini 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 index07
Knowledge benchmarks for DeepSeek V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 3.8 FlashLeader
MMLU ProNot measured90.2%Only Gemini 3.8 Flash measured
LegalBench (Vals AI)83.3%87.0%Gemini 3.8 Flash
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)41.2%48.1%Gemini 3.8 Flash
SimpleQA Verified42.9%69.7%Gemini 3.8 Flash
LMArena Text: science14691523Gemini 3.8 Flash
LMArena Text: medicine and healthcare14841508Gemini 3.8 Flash
LMArena Text: legal and government14431497Gemini 3.8 Flash
LMArena Text: business and finance14611479Gemini 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 index72
Web design benchmarks for DeepSeek V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 3.8 FlashLeader
Design Arena: websites13081300DeepSeek V4.1 Flash
Design Arena: UI components13121316Gemini 3.8 Flash
Design Arena: game dev13301304DeepSeek V4.1 Flash
Design Arena: data viz12911270DeepSeek V4.1 Flash
Design Arena: 3D13551294DeepSeek V4.1 Flash
Design Arena: all code categories13201303DeepSeek V4.1 Flash
Design Arena: SVG12451296Gemini 3.8 Flash
Design Arena: ASCII art12651262DeepSeek V4.1 Flash
LiveBench design79.2%72.7%DeepSeek V4.1 Flash
GeneralLike-for-likePublic boards, shown as published, kept out of the index427
General benchmarks for DeepSeek V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 3.8 FlashLeader
Vals IndexNot measured56.0%Only Gemini 3.8 Flash measured
LiveBench data analysis79.3%54.0%DeepSeek V4.1 Flash
Public Benefits Bench (Vals AI)64.3%65.3%Gemini 3.8 Flash
SAGE (Vals AI)47.9%35.1%DeepSeek V4.1 Flash
MedScribe (Vals AI)85.5%84.5%DeepSeek V4.1 Flash
Long context reasoning (AA-LCR)84.0%84.0%Tie
DTBench89.9%95.7%Gemini 3.8 Flash
LMCA47.0%52.9%Gemini 3.8 Flash
Surface Evolver Bench46.3%76.9%Gemini 3.8 Flash
Furniture assembly34.2%31.7%DeepSeek V4.1 Flash
LMArena Text14641499Gemini 3.8 Flash
LMArena Text: instruction following14731492Gemini 3.8 Flash
LMArena Text: creative writing14371488Gemini 3.8 Flash
LMArena Vision12781315Gemini 3.8 Flash
LMArena Text: English14731498Gemini 3.8 Flash
LMArena Text: non-English14491491Gemini 3.8 Flash
LMArena Text: Chinese15011553Gemini 3.8 Flash
LMArena Text: German14701501Gemini 3.8 Flash
LMArena Text: Japanese14321507Gemini 3.8 Flash
LMArena Text: Korean14361464Gemini 3.8 Flash
LMArena Text: French14651496Gemini 3.8 Flash
LMArena Text: Spanish14591487Gemini 3.8 Flash
LMArena Text: Russian14671514Gemini 3.8 Flash
LMArena Text: Polish14571497Gemini 3.8 Flash
LMArena Text: multi-turn14611503Gemini 3.8 Flash
LMArena Text: longer queries14731507Gemini 3.8 Flash
LMArena Text: writing and language14501494Gemini 3.8 Flash
LMArena Text: entertainment and media14451480Gemini 3.8 Flash
LMArena Vision: English12881318Gemini 3.8 Flash
LMArena Vision: Chinese13271416Gemini 3.8 Flash
LMArena Vision: reading text12821333Gemini 3.8 Flash
LMArena Vision: humor12601321Gemini 3.8 Flash
LMArena Vision: creative writing12751299Gemini 3.8 Flash
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 V4.1 Flash and Gemini 3.8 Flash
BenchmarkDeepSeek V4.1 FlashGemini 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 V4.1 Flash$0.0006Fits in one request
Gemini 3.8 Flash$0.0026Fits in one request

DeepSeek V4.1 Flash costs less

Repository review

50K input + 3K output tokens

DeepSeek V4.1 Flash$0.014Fits in one request
Gemini 3.8 Flash$0.049Fits in one request

DeepSeek V4.1 Flash costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4.1 Flash$0.053Fits in one request
Gemini 3.8 Flash$0.188Fits in one request

DeepSeek V4.1 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 V4.1 Flash and Gemini 3.8 Flash
SpecificationDeepSeek V4.1 FlashGoogle Gemini 3.8 Flash
MakerDeepSeekGoogle
WeightsOpen weightsNo public weights listed
ReleasedSeptember 10, 2026September 2, 2026
Context window1.05M1.05M
Input $/Mtok$0.2225$0.75
Output $/Mtok$0.84$3.75
Coding index62.561.6
Independent measurements behind it56
Cost per solved taskNot computable$2.74
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4.1 Flash better than Gemini 3.8 Flash for coding?

DeepSeek V4.1 Flash and Gemini 3.8 Flash are level for coding, 62.5 against 61.6 on the Vibe Coding Index, so price and context decide. Pick Gemini 3.8 Flash for work measured by ProgramBench (Vals AI) or IOI (Vals AI), where it leads. Pick DeepSeek V4.1 Flash for output tokens 4.5x cheaper ($0.84 vs $3.75 per million) and work measured by LiveBench coding or LMArena WebDev, where it leads.

Which is cheaper, DeepSeek V4.1 Flash or Gemini 3.8 Flash?

DeepSeek V4.1 Flash costs $0.2225 per million input tokens and $0.84 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 V4.1 Flash or Gemini 3.8 Flash?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4.1 Flash vs Gemini 3.8 Flash comparison based on?

101 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4.1 Flash's coding index rests on 5 independent benchmarks 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

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-v4-1-flash-vs-gemini-3-8-flash" title="DeepSeek V4.1 Flash vs Gemini 3.8 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-v4-1-flash-vs-gemini-3-8-flash">LLMBenchmark.ai, DeepSeek V4.1 Flash vs Gemini 3.8 Flash</a></p>