LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

DeepSeek V4.1 Flash vs DeepSeek V4 Pro 0423

Updated October 21, 2026. 68 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V4.1 Flash Replace DeepSeek V4 Pro 0423
DeepSeek V4.1 FlashDeepSeek
Coding
77.2
Overall
24.7
Output $/M
$0.525
57
DeepSeek V4 Pro 0423DeepSeek
Coding
35.3
Overall
30.4
Output $/M
$1.9105
11
vs boards won of 68 shared

Decision reading

Pick DeepSeek V4.1 Flash for coding: it scores 77.2 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423.

Pick DeepSeek V4 Pro 0423 when what matters is AA Intelligence Index or GPQA Diamond (Epoch AI run), where it leads.

Model ADeepSeek V4.1 FlashDeepSeek77.2/1002 independent benchmarksNo cost per solved taskModel BDeepSeek V4 Pro 0423DeepSeek35.3/1001 independent benchmark$0.57 per solved task
Shared results
68
DeepSeek V4.1 Flash only
33
DeepSeek V4 Pro 0423 only
15
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 77.2 from 2 benchmarks, DeepSeek V4 Pro 0423 35.3 from 1 benchmark.
Widest category
Coding, 17.2 points apart on average over 13 shared benchmarks.
Widest single gap
ProofBench: DeepSeek V4.1 Flash 54.0% against DeepSeek V4 Pro 0423 16.0%, 38.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4.1 Flash $0.525 against DeepSeek V4 Pro 0423 $1.9105 per million output tokens, 3.6x 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 FlashBarsDeepSeek V4 Pro 0423Ties
Coding130
Intelligence11
Agentic work40
Reasoning51
Math60
Knowledge43
Web design80
General166
All shared boards5711
CodingLike-for-likeFour of these boards feed the Vibe Coding Index130
Coding benchmarks for DeepSeek V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
LiveBench coding90.2%Not measuredOnly DeepSeek V4.1 Flash measured
LMArena WebDev16181447DeepSeek V4.1 Flash
AA Coding IndexNot measured59.4Only DeepSeek V4 Pro 0423 measured
LiveCodeBench (Vals AI)Not measured87.5%Only DeepSeek V4 Pro 0423 measured
SWE-bench Verified (Vals AI)Not measured77.4%Only DeepSeek V4 Pro 0423 measured
Terminal-Bench 4 (Vals AI)19.7%11.1%DeepSeek V4.1 Flash
Vibe Code Bench (Vals AI)84.7%49.9%DeepSeek V4.1 Flash
Code migration (Vals AI)45.6%26.2%DeepSeek V4.1 Flash
ProgramBench (Vals AI)0.5%0.0%DeepSeek V4.1 Flash
IOI (Vals AI)40.3%Not measuredOnly DeepSeek V4.1 Flash measured
Terminal-Bench 2.1 (Vals AI)74.5%50.2%DeepSeek V4.1 Flash
SWE-bench Multimodal (Vals AI)46.5%Not measuredOnly DeepSeek V4.1 Flash measured
Vibe Code Bench 1-100 (Vals AI)16.4%Not measuredOnly DeepSeek V4.1 Flash measured
SkillsBench (Vals AI)69.8%51.3%DeepSeek V4.1 Flash
CyberBench (Vals AI)73.7%Not measuredOnly DeepSeek V4.1 Flash measured
SciCode51.9%Not measuredOnly DeepSeek V4.1 Flash measured
FrontierCode43.9%17.6%DeepSeek V4.1 Flash
WeirdMLNot measured48.9%Only DeepSeek V4 Pro 0423 measured
ALE-Bench1092.31006.1DeepSeek V4.1 Flash
LMArena Text: coding15021470DeepSeek V4.1 Flash
LMArena Text: software and IT14961469DeepSeek V4.1 Flash
LMArena WebDev: React16281441DeepSeek V4.1 Flash
LMArena WebDev: HTML16121435DeepSeek V4.1 Flash
LMArena WebDev: from an image1606Not measuredOnly DeepSeek V4.1 Flash measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for DeepSeek V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
AA Intelligence Index24.730.4DeepSeek V4 Pro 0423
Epoch Capabilities Index155.9149.1DeepSeek V4.1 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
Agentic work benchmarks for DeepSeek V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
AA Agentic IndexNot measured26.3Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building web appsNot measured1000Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building full-stack appsNot measured948Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building Godot gamesNot measured1059Only DeepSeek V4 Pro 0423 measured
LiveBench research86.8%Not measuredOnly DeepSeek V4.1 Flash measured
LiveBench browser84.0%Not measuredOnly DeepSeek V4.1 Flash measured
LiveBench long agentic40.1%Not measuredOnly DeepSeek V4.1 Flash measured
SREBench (Vals AI)0.8%Not measuredOnly DeepSeek V4.1 Flash measured
Finance Agent (Vals AI)53.5%44.1%DeepSeek V4.1 Flash
Tax Agent Bench (Vals AI)26.6%25.2%DeepSeek V4.1 Flash
Legal Research Bench (Vals AI)41.4%23.1%DeepSeek V4.1 Flash
Excel Modeling Benchmark (Vals AI)57.2%51.6%DeepSeek V4.1 Flash
BioMysteryBench (Vals AI)67.8%Not measuredOnly DeepSeek V4.1 Flash measured
Terminal-Bench-Science (Vals AI)0.0%Not measuredOnly DeepSeek V4.1 Flash measured
Vals Science Index29.6%Not measuredOnly DeepSeek V4.1 Flash measured
APEX-Agents39.5%Not measuredOnly DeepSeek V4.1 Flash measured
Vending-Bench 2Not measured$3,285Only DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
Reasoning benchmarks for DeepSeek V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
GPQA DiamondNot measured89.4%Only DeepSeek V4 Pro 0423 measured
LiveBench reasoning86.7%Not measuredOnly DeepSeek V4.1 Flash measured
MysteryMechanism (Vals AI)21.2%Not measuredOnly DeepSeek V4.1 Flash measured
Humanity's Last Exam (Artificial Analysis run)39.2%Not measuredOnly DeepSeek V4.1 Flash measured
GPQA Diamond (Epoch AI run)89.8%90.9%DeepSeek V4 Pro 0423
ARC-AGI94.5%Not measuredOnly DeepSeek V4.1 Flash measured
ARC-AGI-272.9%Not measuredOnly DeepSeek V4.1 Flash measured
Chess puzzles48.0%19.0%DeepSeek V4.1 Flash
Mystery game puzzles43.0%17.0%DeepSeek V4.1 Flash
LMArena Text: hard prompts14831461DeepSeek V4.1 Flash
LMArena Text: expert15011463DeepSeek V4.1 Flash
LMArena Text: hard prompts in English14881466DeepSeek V4.1 Flash
LMArena Vision: diagrams1297Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Vision: homework1307Not measuredOnly DeepSeek V4.1 Flash measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for DeepSeek V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
OTIS Mock AIME98.3%96.7%DeepSeek V4.1 Flash
FrontierMath, tiers 1 to 367.4%45.3%DeepSeek V4.1 Flash
FrontierMath, tier 426.8%2.4%DeepSeek V4.1 Flash
ProofBench54.0%16.0%DeepSeek V4.1 Flash
LMArena Text: math14781443DeepSeek V4.1 Flash
LMArena Text: mathematical work14851455DeepSeek V4.1 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index43
Knowledge benchmarks for DeepSeek V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
MMLU ProNot measured87.3%Only DeepSeek V4 Pro 0423 measured
LegalBench (Vals AI)83.3%80.3%DeepSeek V4.1 Flash
CaseLaw (Vals AI)Not measured59.4%Only DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)Not measured61.4%Only DeepSeek V4 Pro 0423 measured
TaxEval (Vals AI)Not measured72.1%Only DeepSeek V4 Pro 0423 measured
MedCode (Vals AI)41.2%40.5%DeepSeek V4.1 Flash
SimpleQA Verified42.9%47.0%DeepSeek V4 Pro 0423
LMArena Text: science14691470DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare14841466DeepSeek V4.1 Flash
LMArena Text: legal and government14431464DeepSeek V4 Pro 0423
LMArena Text: business and finance14611443DeepSeek V4.1 Flash
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for DeepSeek V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
Design Arena: websites13091235DeepSeek V4.1 Flash
Design Arena: UI components13141221DeepSeek V4.1 Flash
Design Arena: game dev13311229DeepSeek V4.1 Flash
Design Arena: data viz12901203DeepSeek V4.1 Flash
Design Arena: 3D13561254DeepSeek V4.1 Flash
Design Arena: all code categories13201240DeepSeek V4.1 Flash
Design Arena: SVG12431139DeepSeek V4.1 Flash
Design Arena: ASCII art12651148DeepSeek V4.1 Flash
LiveBench design79.2%Not measuredOnly DeepSeek V4.1 Flash measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index166
General benchmarks for DeepSeek V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
LiveBench data analysis79.3%Not measuredOnly DeepSeek V4.1 Flash measured
Public Benefits Bench (Vals AI)64.3%62.9%DeepSeek V4.1 Flash
SAGE (Vals AI)47.9%Not measuredOnly DeepSeek V4.1 Flash measured
MedScribe (Vals AI)85.5%75.1%DeepSeek V4.1 Flash
Long context reasoning (AA-LCR)84.0%Not measuredOnly DeepSeek V4.1 Flash measured
DTBench89.9%90.7%DeepSeek V4 Pro 0423
LMCA47.0%41.2%DeepSeek V4.1 Flash
Surface Evolver Bench46.3%40.0%DeepSeek V4.1 Flash
Furniture assembly34.2%Not measuredOnly DeepSeek V4.1 Flash measured
CL-bench LifeNot measured13.5%Only DeepSeek V4 Pro 0423 measured
LMArena Text14641451DeepSeek V4.1 Flash
LMArena Text: instruction following14731445DeepSeek V4.1 Flash
LMArena Text: creative writing14371446DeepSeek V4 Pro 0423
LMArena Vision1278Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Text: English14731459DeepSeek V4.1 Flash
LMArena Text: non-English14491439DeepSeek V4.1 Flash
LMArena Text: Chinese15011481DeepSeek V4.1 Flash
LMArena Text: German14701458DeepSeek V4.1 Flash
LMArena Text: Japanese14321446DeepSeek V4 Pro 0423
LMArena Text: Korean14361409DeepSeek V4.1 Flash
LMArena Text: French14651473DeepSeek V4 Pro 0423
LMArena Text: Spanish14591457DeepSeek V4.1 Flash
LMArena Text: Russian14671453DeepSeek V4.1 Flash
LMArena Text: Polish14571461DeepSeek V4 Pro 0423
LMArena Text: multi-turn14611468DeepSeek V4 Pro 0423
LMArena Text: longer queries14731458DeepSeek V4.1 Flash
LMArena Text: writing and language14501447DeepSeek V4.1 Flash
LMArena Text: entertainment and media14451431DeepSeek V4.1 Flash
LMArena Vision: English1288Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Vision: Chinese1327Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Vision: reading text1282Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Vision: humor1260Not measuredOnly DeepSeek V4.1 Flash measured
LMArena Vision: creative writing1275Not measuredOnly DeepSeek V4.1 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 V4.1 Flash and DeepSeek V4 Pro 0423
BenchmarkDeepSeek V4.1 FlashDeepSeek V4 Pro 0423Leader
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$0.0003Fits in one request
DeepSeek V4 Pro 0423$0.0019Fits in one request

DeepSeek V4.1 Flash costs less

Repository review

50K input + 3K output tokens

DeepSeek V4.1 Flash$0.0040Fits in one request
DeepSeek V4 Pro 0423$0.053Fits in one request

DeepSeek V4.1 Flash costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4.1 Flash$0.015Fits in one request
DeepSeek V4 Pro 0423$0.210Fits 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 DeepSeek V4 Pro 0423
SpecificationDeepSeek V4.1 FlashDeepSeek V4 Pro 0423
MakerDeepSeekDeepSeek
WeightsOpen weightsOpen weights
ReleasedSeptember 10, 2026April 24, 2026
Context window1.05M1.05M
Input $/Mtok$0.049$0.9553
Output $/Mtok$0.525$1.9105
Coding index77.235.3
Independent measurements behind it21
Cost per solved taskNot computable$0.57
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4.1 Flash better than DeepSeek V4 Pro 0423 for coding?

Pick DeepSeek V4.1 Flash for coding: it scores 77.2 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 when what matters is AA Intelligence Index or GPQA Diamond (Epoch AI run), where it leads.

Which is cheaper, DeepSeek V4.1 Flash or DeepSeek V4 Pro 0423?

DeepSeek V4.1 Flash costs $0.049 per million input tokens and $0.525 per million output tokens; DeepSeek V4 Pro 0423 costs $0.9553 and $1.9105. Cost per solved task is known for DeepSeek V4 Pro 0423 only.

Which has the bigger context window, DeepSeek V4.1 Flash or DeepSeek V4 Pro 0423?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4.1 Flash vs DeepSeek V4 Pro 0423 comparison based on?

68 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4.1 Flash's coding index rests on 2 independent benchmarks and DeepSeek V4 Pro 0423's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next