Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0813 vs MiniMax M3

DeepSeek V4 Pro 0813 leads MiniMax M3 on coding, 56.1 to 39.2 on the Vibe Coding Index, and MiniMax M3 costs 1.7x less per output token ($1.20 vs $1.98 per million). Updated October 22, 2026; 66 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0813 Replace MiniMax M3
DeepSeek V4 Pro 0813DeepSeek
Coding
56.1
Overall
60.8
Output $/M
$1.98
55
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
11
vs boards won of 66 shared

DeepSeek V4 Pro 0813 or MiniMax M3: which to pick

Pick DeepSeek V4 Pro 0813 for coding: it scores 56.1 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 5 benchmarks against 6.

Pick MiniMax M3 for output tokens 1.7x cheaper ($1.20 vs $1.98 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model ADeepSeek V4 Pro 0813DeepSeek56.1/1005 independent benchmarks$0.10 per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
66
DeepSeek V4 Pro 0813 only
12
MiniMax M3 only
50
Like-for-like categories
7 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 0813 56.1 from 5 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Math, 15.6 points apart on average over 4 shared benchmarks.
Widest single gap
Mystery game puzzles: DeepSeek V4 Pro 0813 43.0% against MiniMax M3 8.0%, 35.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0813 $1.98 against MiniMax M3 $1.20 per million output tokens, 1.7x 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 0813BarsMiniMax M3Ties
Coding162
Intelligence20
Agentic work60
Reasoning63
Math31
Knowledge63
General162
All shared boards5511
CodingLike-for-likeSix of these boards feed the Vibe Coding Index162
Coding benchmarks for DeepSeek V4 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax M3Leader
LiveBench codingNot measured70.9%Only MiniMax M3 measured
LMArena WebDev15821482DeepSeek V4 Pro 0813
AA Coding Index68.858.6DeepSeek V4 Pro 0813
LiveCodeBench (Vals AI)87.5%82.2%DeepSeek V4 Pro 0813
SWE-bench Verified (Vals AI)96.4%75.0%DeepSeek V4 Pro 0813
Terminal-Bench 4 (Vals AI)14.1%1.0%DeepSeek V4 Pro 0813
Vibe Code Bench (Vals AI)82.3%47.6%DeepSeek V4 Pro 0813
Code migration (Vals AI)41.5%19.9%DeepSeek V4 Pro 0813
ProgramBench (Vals AI)0.0%Not measuredOnly DeepSeek V4 Pro 0813 measured
IOI (Vals AI)51.6%Not measuredOnly DeepSeek V4 Pro 0813 measured
Terminal-Bench 2.1 (Vals AI)54.7%53.6%DeepSeek V4 Pro 0813
SWE-bench Multimodal (Vals AI)Not measured33.3%Only MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)17.5%9.2%DeepSeek V4 Pro 0813
SkillsBench (Vals AI)53.8%51.5%DeepSeek V4 Pro 0813
CyberBench (Vals AI)72.9%65.0%DeepSeek V4 Pro 0813
SciCode51.0%47.1%DeepSeek V4 Pro 0813
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCode28.5%14.7%DeepSeek V4 Pro 0813
WeirdML66.2%Not measuredOnly DeepSeek V4 Pro 0813 measured
ALE-Bench1403.2640.0DeepSeek V4 Pro 0813
LMArena Text: coding14691470MiniMax M3
LMArena Text: software and IT14621466MiniMax M3
LMArena WebDev: React15881478DeepSeek V4 Pro 0813
LMArena WebDev: HTML15661455DeepSeek V4 Pro 0813
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 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax M3Leader
AA Intelligence Index36.029.2DeepSeek V4 Pro 0813
Epoch Capabilities Index155.6146.9DeepSeek V4 Pro 0813
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for DeepSeek V4 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax M3Leader
AA Agentic Index41.329.5DeepSeek V4 Pro 0813
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
SREBench (Vals AI)1.9%Not measuredOnly DeepSeek V4 Pro 0813 measured
Finance Agent (Vals AI)50.4%48.3%DeepSeek V4 Pro 0813
Tax Agent Bench (Vals AI)26.8%20.6%DeepSeek V4 Pro 0813
Legal Research Bench (Vals AI)40.9%29.8%DeepSeek V4 Pro 0813
Harvey's Legal Agent Benchmark (Vals AI)10.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
Excel Modeling Benchmark (Vals AI)52.8%47.8%DeepSeek V4 Pro 0813
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly DeepSeek V4 Pro 0813 measured
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-Agents47.3%37.7%DeepSeek V4 Pro 0813
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 18 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index63
Reasoning benchmarks for DeepSeek V4 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax M3Leader
GPQA Diamond92.4%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)92.8%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)41.0%39.0%DeepSeek V4 Pro 0813
GPQA Diamond (Epoch AI run)91.7%90.9%DeepSeek V4 Pro 0813
ARC-AGI90.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
ARC-AGI-261.3%Not measuredOnly DeepSeek V4 Pro 0813 measured
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzles46.0%13.0%DeepSeek V4 Pro 0813
Mystery game puzzles43.0%8.0%DeepSeek V4 Pro 0813
LMArena Text: hard prompts14581447DeepSeek V4 Pro 0813
LMArena Text: expert14591461MiniMax M3
LMArena Text: hard prompts in English14631455DeepSeek V4 Pro 0813
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 index31
Math benchmarks for DeepSeek V4 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax M3Leader
OTIS Mock AIME98.6%71.1%DeepSeek V4 Pro 0813
FrontierMath, tiers 1 to 364.6%Not measuredOnly DeepSeek V4 Pro 0813 measured
FrontierMath, tier 426.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
ProofBench50.0%18.0%DeepSeek V4 Pro 0813
LMArena Text: math14411429DeepSeek V4 Pro 0813
LMArena Text: mathematical work14431448MiniMax M3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index63
Knowledge benchmarks for DeepSeek V4 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax M3Leader
MMLU Pro87.0%84.2%DeepSeek V4 Pro 0813
LegalBench (Vals AI)82.4%85.4%MiniMax M3
CorpFin (Vals AI)65.4%68.1%MiniMax M3
TaxEval (Vals AI)73.1%72.7%DeepSeek V4 Pro 0813
MortgageTax (Vals AI)Not measured68.4%Only MiniMax M3 measured
MedCode (Vals AI)42.5%46.3%MiniMax M3
SimpleQA Verified52.9%Not measuredOnly DeepSeek V4 Pro 0813 measured
LMArena Text: science14571452DeepSeek V4 Pro 0813
LMArena Text: medicine and healthcare14461441DeepSeek V4 Pro 0813
LMArena Text: legal and government14591437DeepSeek V4 Pro 0813
LMArena Text: business and finance14421434DeepSeek V4 Pro 0813
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for DeepSeek V4 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax M3Leader
Design Arena: websitesNot measured1257Only MiniMax M3 measured
Design Arena: UI componentsNot measured1242Only MiniMax M3 measured
Design Arena: game devNot measured1210Only MiniMax M3 measured
Design Arena: data vizNot measured1236Only MiniMax M3 measured
Design Arena: 3DNot measured1208Only MiniMax M3 measured
Design Arena: all code categoriesNot measured1247Only MiniMax M3 measured
Design Arena: SVGNot measured1161Only MiniMax M3 measured
Design Arena: ASCII artNot measured1161Only MiniMax M3 measured
LiveBench designNot measured66.2%Only MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index162
General benchmarks for DeepSeek V4 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax M3Leader
Vals Index53.0%Not measuredOnly DeepSeek V4 Pro 0813 measured
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)80.2%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)80.3%83.0%MiniMax M3
DTBench93.9%78.9%DeepSeek V4 Pro 0813
LMCA45.5%33.7%DeepSeek V4 Pro 0813
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
LMArena Text14461433DeepSeek V4 Pro 0813
LMArena Text: instruction following14481433DeepSeek V4 Pro 0813
LMArena Text: creative writing14391404DeepSeek V4 Pro 0813
LMArena VisionNot measured1251Only MiniMax M3 measured
LMArena Text: English14571443DeepSeek V4 Pro 0813
LMArena Text: non-English14311420DeepSeek V4 Pro 0813
LMArena Text: Chinese14811466DeepSeek V4 Pro 0813
LMArena Text: GermanNot measured1428Only MiniMax M3 measured
LMArena Text: JapaneseNot measured1380Only MiniMax M3 measured
LMArena Text: Korean14491373DeepSeek V4 Pro 0813
LMArena Text: French14461444DeepSeek V4 Pro 0813
LMArena Text: Spanish14351433DeepSeek V4 Pro 0813
LMArena Text: Russian14481426DeepSeek V4 Pro 0813
LMArena Text: PolishNot measured1423Only MiniMax M3 measured
LMArena Text: multi-turn14541443DeepSeek V4 Pro 0813
LMArena Text: longer queries14581446DeepSeek V4 Pro 0813
LMArena Text: writing and language14431419DeepSeek V4 Pro 0813
LMArena Text: entertainment and media14241403DeepSeek V4 Pro 0813
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 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Pro 0813 and MiniMax M3
BenchmarkDeepSeek V4 Pro 0813MiniMax 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 Pro 0813$0.0016Fits in one request
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0813$0.039Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0813$0.152Fits in one request
MiniMax M3$0.072Fits in one request

MiniMax M3 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 0813 and MiniMax M3
SpecificationDeepSeek V4 Pro 0813MiniMax M3
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedAugust 12, 2026May 31, 2026
Context window1.05M1.05M
Input $/Mtok$0.66$0.30
Output $/Mtok$1.98$1.20
Coding index56.139.2
Independent measurements behind it56
Cost per solved task$0.10$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0813 better than MiniMax M3 for coding?

Pick DeepSeek V4 Pro 0813 for coding: it scores 56.1 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 5 benchmarks against 6. Pick MiniMax M3 for output tokens 1.7x cheaper ($1.20 vs $1.98 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, DeepSeek V4 Pro 0813 or MiniMax M3?

DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0813 costs $0.10 and MiniMax M3 $0.56.

Which has the bigger context window, DeepSeek V4 Pro 0813 or MiniMax M3?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0813 vs MiniMax M3 comparison based on?

66 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Pro 0813's coding index rests on 5 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-pro-0813-vs-minimax-minimax-m3" title="DeepSeek V4 Pro 0813 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-pro-0813-vs-minimax-minimax-m3">LLMBenchmark.ai, DeepSeek V4 Pro 0813 vs MiniMax M3</a></p>