Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0731 vs MiniMax M3

DeepSeek V4 Flash 0731 leads MiniMax M3 on coding, 51.8 to 39.2 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 3.0x less per output token ($0.396 vs $1.20 per million). Updated October 22, 2026; 45 benchmarks have a result for both.

Replace DeepSeek V4 Flash 0731 Replace MiniMax M3
DeepSeek V4 Flash 0731DeepSeek
Coding
51.8
Overall
55.2
Output $/M
$0.396
28
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
16
vs boards won of 45 shared, 1 tied

DeepSeek V4 Flash 0731 or MiniMax M3: which to pick

Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 4 benchmarks against 6.

Pick MiniMax M3 for work measured by SkillsBench (Vals AI) or GPQA Diamond, where it leads.

Model ADeepSeek V4 Flash 0731DeepSeek51.8/1004 independent benchmarks$0.01 per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
45
DeepSeek V4 Flash 0731 only
10
MiniMax M3 only
71
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 0731 51.8 from 4 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Math, 30.7 points apart on average over 2 shared benchmarks.
Widest single gap
ProofBench: DeepSeek V4 Flash 0731 56.0% against MiniMax M3 18.0%, 38.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0731 $0.396 against MiniMax M3 $1.20 per million output tokens, 3.0x 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 0731BarsMiniMax M3Ties
Coding111
Intelligence20
Agentic work50
Reasoning43
Math20
Knowledge14
Web design161 tie
General22
All shared boards28161 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index111
Coding benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
LiveBench codingNot measured70.9%Only MiniMax M3 measured
LMArena WebDevNot measured1482Only MiniMax M3 measured
AA Coding Index69.158.6DeepSeek V4 Flash 0731
LiveCodeBench (Vals AI)87.3%82.2%DeepSeek V4 Flash 0731
SWE-bench Verified (Vals AI)88.8%75.0%DeepSeek V4 Flash 0731
Terminal-Bench 4 (Vals AI)18.7%1.0%DeepSeek V4 Flash 0731
Vibe Code Bench (Vals AI)74.7%47.6%DeepSeek V4 Flash 0731
Code migration (Vals AI)38.6%19.9%DeepSeek V4 Flash 0731
ProgramBench (Vals AI)0.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
IOI (Vals AI)32.7%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench 2.1 (Vals AI)67.0%53.6%DeepSeek V4 Flash 0731
SWE-bench Multimodal (Vals AI)Not measured33.3%Only MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured9.2%Only MiniMax M3 measured
SkillsBench (Vals AI)50.7%51.5%MiniMax M3
CyberBench (Vals AI)72.1%65.0%DeepSeek V4 Flash 0731
SciCode50.3%47.1%DeepSeek V4 Flash 0731
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCode18.8%14.7%DeepSeek V4 Flash 0731
WeirdML63.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
ALE-Bench1306.1640.0DeepSeek V4 Flash 0731
LMArena Text: codingNot measured1470Only MiniMax M3 measured
LMArena Text: software and ITNot measured1466Only MiniMax M3 measured
LMArena WebDev: ReactNot measured1478Only MiniMax M3 measured
LMArena WebDev: HTMLNot measured1455Only MiniMax M3 measured
LMArena WebDev: from an imageNot measured1470Only MiniMax M3 measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
AA Intelligence Index34.329.2DeepSeek V4 Flash 0731
Epoch Capabilities Index154.8146.9DeepSeek V4 Flash 0731
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
AA Agentic Index41.029.5DeepSeek V4 Flash 0731
Design Arena: agents building web appsNot measured1200Only MiniMax M3 measured
Design Arena: agents building full-stack appsNot measured1197Only MiniMax M3 measured
Design Arena: agents building mobile appsNot measured1169Only MiniMax M3 measured
Design Arena: agents building Android appsNot measured1159Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1158Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1130Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1181Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1028Only MiniMax M3 measured
LiveBench researchNot measured68.0%Only MiniMax M3 measured
LiveBench browserNot measured8.0%Only MiniMax M3 measured
LiveBench long agenticNot measured12.4%Only MiniMax M3 measured
Finance Agent (Vals AI)49.5%48.3%DeepSeek V4 Flash 0731
Tax Agent Bench (Vals AI)28.1%20.6%DeepSeek V4 Flash 0731
Legal Research Bench (Vals AI)30.3%29.8%DeepSeek V4 Flash 0731
Excel Modeling Benchmark (Vals AI)57.0%47.8%DeepSeek V4 Flash 0731
BioMysteryBench (Vals AI)64.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly DeepSeek V4 Flash 0731 measured
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-AgentsNot measured37.7%Only MiniMax M3 measured
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
Vending-Bench 2Not measured$2,158Only MiniMax M3 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index43
Reasoning benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
GPQA Diamond89.9%92.7%MiniMax M3
LiveBench reasoningNot measured74.5%Only MiniMax M3 measured
MMMU Pro (Vals AI)Not measured81.2%Only MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)90.8%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)38.6%39.0%MiniMax M3
GPQA Diamond (Epoch AI run)91.0%90.9%DeepSeek V4 Flash 0731
ARC-AGI89.0%Not measuredOnly DeepSeek V4 Flash 0731 measured
ARC-AGI-261.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
SimpleBench61.1%45.8%DeepSeek V4 Flash 0731
Chess puzzles32.0%13.0%DeepSeek V4 Flash 0731
Mystery game puzzles34.0%8.0%DeepSeek V4 Flash 0731
LMArena Text: hard promptsNot measured1447Only MiniMax M3 measured
LMArena Text: expertNot measured1461Only MiniMax M3 measured
LMArena Text: hard prompts in EnglishNot measured1455Only MiniMax M3 measured
LMArena Vision: diagramsNot measured1266Only MiniMax M3 measured
LMArena Vision: homeworkNot measured1268Only MiniMax M3 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
OTIS Mock AIME94.4%71.1%DeepSeek V4 Flash 0731
FrontierMath, tiers 1 to 357.5%Not measuredOnly DeepSeek V4 Flash 0731 measured
FrontierMath, tier 424.4%Not measuredOnly DeepSeek V4 Flash 0731 measured
ProofBench56.0%18.0%DeepSeek V4 Flash 0731
LMArena Text: mathNot measured1429Only MiniMax M3 measured
LMArena Text: mathematical workNot measured1448Only MiniMax M3 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index14
Knowledge benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
MMLU Pro86.2%84.2%DeepSeek V4 Flash 0731
LegalBench (Vals AI)77.7%85.4%MiniMax M3
CorpFin (Vals AI)61.9%68.1%MiniMax M3
TaxEval (Vals AI)70.7%72.7%MiniMax M3
MortgageTax (Vals AI)Not measured68.4%Only MiniMax M3 measured
MedCode (Vals AI)41.4%46.3%MiniMax M3
SimpleQA Verified33.6%Not measuredOnly DeepSeek V4 Flash 0731 measured
LMArena Text: scienceNot measured1452Only MiniMax M3 measured
LMArena Text: medicine and healthcareNot measured1441Only MiniMax M3 measured
LMArena Text: legal and governmentNot measured1437Only MiniMax M3 measured
LMArena Text: business and financeNot measured1434Only MiniMax M3 measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index16
Web design benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
Design Arena: websites12371257MiniMax M3
Design Arena: UI components12331242MiniMax M3
Design Arena: game dev12071210MiniMax M3
Design Arena: data viz11801236MiniMax M3
Design Arena: 3D12081208Tie
Design Arena: all code categories12291247MiniMax M3
Design Arena: SVG11841161DeepSeek V4 Flash 0731
Design Arena: ASCII art10901161MiniMax M3
LiveBench designNot measured66.2%Only MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index22
General benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
LiveBench data analysisNot measured76.2%Only MiniMax M3 measured
Public Benefits Bench (Vals AI)Not measured64.1%Only MiniMax M3 measured
SAGE (Vals AI)Not measured50.6%Only MiniMax M3 measured
MedScribe (Vals AI)80.4%87.3%MiniMax M3
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)79.7%83.0%MiniMax M3
DTBench90.9%78.9%DeepSeek V4 Flash 0731
LMCA41.7%33.7%DeepSeek V4 Flash 0731
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
LMArena TextNot measured1433Only MiniMax M3 measured
LMArena Text: instruction followingNot measured1433Only MiniMax M3 measured
LMArena Text: creative writingNot measured1404Only MiniMax M3 measured
LMArena VisionNot measured1251Only MiniMax M3 measured
LMArena Text: EnglishNot measured1443Only MiniMax M3 measured
LMArena Text: non-EnglishNot measured1420Only MiniMax M3 measured
LMArena Text: ChineseNot measured1466Only MiniMax M3 measured
LMArena Text: GermanNot measured1428Only MiniMax M3 measured
LMArena Text: JapaneseNot measured1380Only MiniMax M3 measured
LMArena Text: KoreanNot measured1373Only MiniMax M3 measured
LMArena Text: FrenchNot measured1444Only MiniMax M3 measured
LMArena Text: SpanishNot measured1433Only MiniMax M3 measured
LMArena Text: RussianNot measured1426Only MiniMax M3 measured
LMArena Text: PolishNot measured1423Only MiniMax M3 measured
LMArena Text: multi-turnNot measured1443Only MiniMax M3 measured
LMArena Text: longer queriesNot measured1446Only MiniMax M3 measured
LMArena Text: writing and languageNot measured1419Only MiniMax M3 measured
LMArena Text: entertainment and mediaNot measured1403Only MiniMax M3 measured
LMArena Vision: EnglishNot measured1263Only MiniMax M3 measured
LMArena Vision: ChineseNot measured1311Only MiniMax M3 measured
LMArena Vision: reading textNot measured1259Only MiniMax M3 measured
LMArena Vision: humorNot measured1235Only MiniMax M3 measured
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writingNot measured1234Only MiniMax M3 measured
LMArena DocumentNot measured1435Only MiniMax M3 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Flash 0731 and MiniMax M3
BenchmarkDeepSeek V4 Flash 0731MiniMax M3Leader
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 0731$0.0003Fits in one request
MiniMax M3$0.0009Fits in one request

DeepSeek V4 Flash 0731 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Flash 0731$0.0082Fits in one request
MiniMax M3$0.019Fits in one request

DeepSeek V4 Flash 0731 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0731$0.032Fits in one request
MiniMax M3$0.072Fits in one request

DeepSeek V4 Flash 0731 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 0731 and MiniMax M3
SpecificationDeepSeek V4 Flash 0731MiniMax M3
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedJuly 31, 2026May 31, 2026
Context window1.05M1.05M
Input $/Mtok$0.14$0.30
Output $/Mtok$0.396$1.20
Coding index51.839.2
Independent measurements behind it46
Cost per solved task$0.01$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Flash 0731 better than MiniMax M3 for coding?

Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 4 benchmarks against 6. Pick MiniMax M3 for work measured by SkillsBench (Vals AI) or GPQA Diamond, where it leads.

Which is cheaper, DeepSeek V4 Flash 0731 or MiniMax M3?

DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.396 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, DeepSeek V4 Flash 0731 costs $0.01 and MiniMax M3 $0.56.

Which has the bigger context window, DeepSeek V4 Flash 0731 or MiniMax M3?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Flash 0731 vs MiniMax M3 comparison based on?

45 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Flash 0731's coding index rests on 4 independent benchmarks and MiniMax M3'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-flash-0731-vs-minimax-minimax-m3" title="DeepSeek V4 Flash 0731 vs MiniMax M3, 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-flash-0731-vs-minimax-minimax-m3">LLMBenchmark.ai, DeepSeek V4 Flash 0731 vs MiniMax M3</a></p>