LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs MiniMax M3

Updated October 21, 2026. 60 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V3.2 Replace MiniMax M3
DeepSeek V3.2DeepSeek
Coding
54.4
Overall
21.5
Output $/M
$0.42
4
MiniMax M3MiniMax
Coding
57.8
Overall
29.2
Output $/M
$1.20
56
vs boards won of 60 shared

Decision reading

Pick MiniMax M3 for coding: it scores 57.8 on the Vibe Coding Index against 54.4 for DeepSeek V3.2.

Pick DeepSeek V3.2 when output tokens cost 2.9x less, or when what matters is τ²-Bench Telecom or LMArena Text: math, where it leads.

Model ADeepSeek V3.2DeepSeek54.4/1002 independent benchmarks$0.99 per solved taskModel BMiniMax M3MiniMax57.8/1002 independent benchmarks$0.56 per solved task
Shared results
60
DeepSeek V3.2 only
15
MiniMax M3 only
56
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 V3.2 54.4 from 2 benchmarks, MiniMax M3 57.8 from 2 benchmarks.
Widest category
Coding, 13.1 points apart on average over 10 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): DeepSeek V3.2 5.1% against MiniMax M3 47.6%, 42.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.42 against MiniMax M3 $1.20 per million output tokens, 2.9x apart.
Context window
DeepSeek V3.2 takes 164K tokens, MiniMax M3 1.05M.

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 V3.2BarsMiniMax M3Ties
Coding010
Intelligence02
Agentic work12
Reasoning06
Math11
Knowledge17
Web design08
General120
All shared boards456
CodingLike-for-likeFour of these boards feed the Vibe Coding Index010
Coding benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax M3Leader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LiveBench codingNot measured70.9%Only MiniMax M3 measured
LMArena WebDev13621482MiniMax M3
AA Coding Index44.258.6MiniMax M3
LiveCodeBench (Vals AI)80.7%82.2%MiniMax M3
SWE-bench Verified (Vals AI)67.6%75.0%MiniMax M3
Terminal-Bench 4 (Vals AI)Not measured1.0%Only MiniMax M3 measured
Vibe Code Bench (Vals AI)5.1%47.6%MiniMax M3
Code migration (Vals AI)Not measured19.9%Only MiniMax M3 measured
Terminal-Bench 2.1 (Vals AI)Not measured53.6%Only MiniMax M3 measured
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)Not measured51.5%Only MiniMax M3 measured
CyberBench (Vals AI)Not measured65.0%Only MiniMax M3 measured
LiveCodeBench (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
SciCodeNot measured47.1%Only MiniMax M3 measured
Terminal-Bench Hard (Artificial Analysis run)35.6%42.4%MiniMax M3
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
FrontierCodeNot measured14.7%Only MiniMax M3 measured
ALE-BenchNot measured640.0Only MiniMax M3 measured
LMArena Text: coding14531470MiniMax M3
LMArena Text: software and IT14491466MiniMax M3
LMArena WebDev: React13501478MiniMax M3
LMArena WebDev: HTML13711455MiniMax M3
LMArena WebDev: from an imageNot measured1470Only MiniMax M3 measured
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax M3Leader
AA Intelligence Index21.529.2MiniMax M3
Epoch Capabilities Index146.1146.9MiniMax M3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index12
Agentic work benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax M3Leader
AA Agentic IndexNot measured29.5Only MiniMax M3 measured
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 measured1164Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1158Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1180Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1205Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1021Only 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)Not measured48.3%Only MiniMax M3 measured
Tax Agent Bench (Vals AI)Not measured20.6%Only MiniMax M3 measured
Legal Research Bench (Vals AI)Not measured29.8%Only MiniMax M3 measured
Excel Modeling Benchmark (Vals AI)Not measured47.8%Only MiniMax M3 measured
τ²-Bench Telecom90.6%88.9%DeepSeek V3.2
APEX-Agents21.3%37.7%MiniMax M3
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
Vending-Bench 2$1,034$2,158MiniMax M3
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax M3Leader
GPQA Diamond80.3%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)84.0%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)24.6%39.0%MiniMax M3
GPQA Diamond (Epoch AI run)Not measured90.9%Only MiniMax M3 measured
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzlesNot measured13.0%Only MiniMax M3 measured
Mystery game puzzlesNot measured8.0%Only MiniMax M3 measured
LMArena Text: hard prompts14341447MiniMax M3
LMArena Text: expert14361461MiniMax M3
LMArena Text: hard prompts in English14461455MiniMax M3
LMArena Vision: diagramsNot measured1266Only MiniMax M3 measured
LMArena Vision: homeworkNot measured1268Only MiniMax M3 measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index11
Math benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax M3Leader
AIME84.6%Not measuredOnly DeepSeek V3.2 measured
MGSM (Vals AI)86.0%Not measuredOnly DeepSeek V3.2 measured
AA Math Index92.0Not measuredOnly DeepSeek V3.2 measured
AIME 2025 (Artificial Analysis run)92.0%Not measuredOnly DeepSeek V3.2 measured
OTIS Mock AIMENot measured71.1%Only MiniMax M3 measured
ProofBenchNot measured18.0%Only MiniMax M3 measured
LMArena Text: math14351429DeepSeek V3.2
LMArena Text: mathematical work14401448MiniMax M3
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index17
Knowledge benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax M3Leader
MMLU Pro84.9%84.2%DeepSeek V3.2
LegalBench (Vals AI)76.1%85.4%MiniMax M3
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%68.1%MiniMax M3
TaxEval (Vals AI)68.2%72.7%MiniMax M3
MortgageTax (Vals AI)Not measured68.4%Only MiniMax M3 measured
MedQA (Vals AI)93.9%Not measuredOnly DeepSeek V3.2 measured
MedCode (Vals AI)Not measured46.3%Only MiniMax M3 measured
MMLU Pro (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: science14461452MiniMax M3
LMArena Text: medicine and healthcare14401441MiniMax M3
LMArena Text: legal and government14251437MiniMax M3
LMArena Text: business and finance14101434MiniMax M3
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax M3Leader
Design Arena: websites11751257MiniMax M3
Design Arena: UI components11491246MiniMax M3
Design Arena: game dev11321210MiniMax M3
Design Arena: data viz11581235MiniMax M3
Design Arena: 3D11331209MiniMax M3
Design Arena: all code categories11641247MiniMax M3
Design Arena: SVG10321161MiniMax M3
Design Arena: ASCII art10821161MiniMax M3
LiveBench designNot measured66.2%Only MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index120
General benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax 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)Not measured87.3%Only MiniMax M3 measured
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBench60.7%82.9%MiniMax M3
Long context reasoning (AA-LCR)73.3%83.0%MiniMax M3
DTBench85.6%78.9%DeepSeek V3.2
LMCA28.8%33.7%MiniMax M3
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251433MiniMax M3
LMArena Text: instruction following14131433MiniMax M3
LMArena Text: creative writing14001404MiniMax M3
LMArena VisionNot measured1251Only MiniMax M3 measured
LMArena Text: English14391443MiniMax M3
LMArena Text: non-English14091420MiniMax M3
LMArena Text: Chinese14551466MiniMax M3
LMArena Text: German14131428MiniMax M3
LMArena Text: Japanese13741380MiniMax M3
LMArena Text: Korean13701373MiniMax M3
LMArena Text: French14291444MiniMax M3
LMArena Text: Spanish14241433MiniMax M3
LMArena Text: Russian14241426MiniMax M3
LMArena Text: Polish14191423MiniMax M3
LMArena Text: multi-turn14271443MiniMax M3
LMArena Text: longer queries14281446MiniMax M3
LMArena Text: writing and language14071419MiniMax M3
LMArena Text: entertainment and media13951403MiniMax M3
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 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.2 and MiniMax M3
BenchmarkDeepSeek V3.2MiniMax 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 V3.2$0.0005Fits in one request
MiniMax M3$0.0009Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.015Fits in one request
MiniMax M3$0.019Fits in one request

DeepSeek V3.2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.060Exceeds the context window
MiniMax M3$0.072Fits in one request

DeepSeek V3.2 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 V3.2 and MiniMax M3
SpecificationDeepSeek V3.2MiniMax M3
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025May 31, 2026
Context window164K1.05M
Input $/Mtok$0.28$0.30
Output $/Mtok$0.42$1.20
Coding index54.457.8
Independent measurements behind it22
Cost per solved task$0.99$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than MiniMax M3 for coding?

Pick MiniMax M3 for coding: it scores 57.8 on the Vibe Coding Index against 54.4 for DeepSeek V3.2. Pick DeepSeek V3.2 when output tokens cost 2.9x less, or when what matters is τ²-Bench Telecom or LMArena Text: math, where it leads.

Which is cheaper, DeepSeek V3.2 or MiniMax M3?

DeepSeek V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and MiniMax M3 $0.56.

Which has the bigger context window, DeepSeek V3.2 or MiniMax M3?

MiniMax M3, with 1.05M tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs MiniMax M3 comparison based on?

60 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 2 independent benchmarks and MiniMax M3's on 2. 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-v3-2-vs-minimax-minimax-m3" title="DeepSeek V3.2 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-v3-2-vs-minimax-minimax-m3">LLMBenchmark.ai, DeepSeek V3.2 vs MiniMax M3</a></p>