Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs MiniMax M2.7

MiniMax M2.7 leads DeepSeek V3.2 on coding, 36.2 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 1.4x less per output token ($0.88 vs $1.20 per million). Updated October 22, 2026; 59 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace MiniMax M2.7
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
31
MiniMax M2.7MiniMax
Coding
36.2
Overall
44.5
Output $/M
$1.20
28
vs boards won of 59 shared

DeepSeek V3.2 or MiniMax M2.7: which to pick

Pick MiniMax M2.7 for coding: it scores 36.2 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.

Pick DeepSeek V3.2 for output tokens 1.4x cheaper ($0.88 vs $1.20 per million) and work measured by LiveCodeBench (Vals AI) or LMArena Text: software and IT, where it leads.

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BMiniMax M2.7MiniMax36.2/1003 independent benchmarks$0.64 per solved task
Shared results
59
DeepSeek V3.2 only
16
MiniMax M2.7 only
15
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 V3.2 30.0 from 3 benchmarks, MiniMax M2.7 36.2 from 3 benchmarks.
Widest category
Web design, 9.0 points apart on average over 8 shared benchmarks.
Widest single gap
LMArena Text: Japanese: DeepSeek V3.2 1374 against MiniMax M2.7 1260, 19.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against MiniMax M2.7 $1.20 per million output tokens, 1.4x apart.
Context window
DeepSeek V3.2 takes 164K tokens, MiniMax M2.7 205K.

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 M2.7Ties
Coding29
Intelligence11
Agentic work10
Reasoning24
Math21
Knowledge63
Web design08
General172
All shared boards3128
CodingLike-for-likeSix of these boards feed the Vibe Coding Index29
Coding benchmarks for DeepSeek V3.2 and MiniMax M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev13621399MiniMax M2.7
AA Coding Index44.252.6MiniMax M2.7
LiveCodeBench (Vals AI)80.7%79.9%DeepSeek V3.2
SWE-bench Verified (Vals AI)67.6%73.8%MiniMax M2.7
Vibe Code Bench (Vals AI)5.1%11.9%MiniMax M2.7
Code migration (Vals AI)Not measured8.7%Only MiniMax M2.7 measured
ProgramBench (Vals AI)Not measured0.0%Only MiniMax M2.7 measured
Terminal-Bench 2.1 (Vals AI)Not measured48.7%Only MiniMax M2.7 measured
LiveCodeBench (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
SciCodeNot measured50.1%Only MiniMax M2.7 measured
Terminal-Bench Hard (Artificial Analysis run)35.6%39.4%MiniMax M2.7
Terminal-Bench39.6%45.1%MiniMax M2.7
WeirdMLNot measured37.0%Only MiniMax M2.7 measured
ALE-BenchNot measured599.3Only MiniMax M2.7 measured
LMArena Text: coding14531454MiniMax M2.7
LMArena Text: software and IT14491446DeepSeek V3.2
LMArena WebDev: React13501388MiniMax M2.7
LMArena WebDev: HTML13711401MiniMax M2.7
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for DeepSeek V3.2 and MiniMax M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
AA Intelligence Index21.522.8MiniMax M2.7
Epoch Capabilities Index146.1145.8DeepSeek V3.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.2 and MiniMax M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
AA Agentic IndexNot measured15.3Only MiniMax M2.7 measured
Finance Agent (Vals AI)Not measured27.9%Only MiniMax M2.7 measured
Tax Agent Bench (Vals AI)Not measured6.9%Only MiniMax M2.7 measured
Legal Research Bench (Vals AI)Not measured10.6%Only MiniMax M2.7 measured
Excel Modeling Benchmark (Vals AI)Not measured28.4%Only MiniMax M2.7 measured
τ²-Bench Telecom90.6%84.8%DeepSeek V3.2
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index24
Reasoning benchmarks for DeepSeek V3.2 and MiniMax M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
GPQA Diamond80.3%86.6%MiniMax M2.7
GPQA Diamond (Artificial Analysis run)84.0%87.4%MiniMax M2.7
Humanity's Last Exam (Artificial Analysis run)24.6%29.6%MiniMax M2.7
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: hard prompts14341422DeepSeek V3.2
LMArena Text: expert14361443MiniMax M2.7
LMArena Text: hard prompts in English14461441DeepSeek V3.2
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index21
Math benchmarks for DeepSeek V3.2 and MiniMax M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
AIME84.6%91.0%MiniMax M2.7
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
ProofBenchNot measured3.0%Only MiniMax M2.7 measured
LMArena Text: math14351421DeepSeek V3.2
LMArena Text: mathematical work14401437DeepSeek V3.2
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index63
Knowledge benchmarks for DeepSeek V3.2 and MiniMax M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
MMLU Pro84.9%80.4%DeepSeek V3.2
LegalBench (Vals AI)76.1%84.0%MiniMax M2.7
CaseLaw (Vals AI)55.4%60.9%MiniMax M2.7
CorpFin (Vals AI)51.0%61.2%MiniMax M2.7
TaxEval (Vals AI)68.2%66.6%DeepSeek V3.2
MedQA (Vals AI)93.9%Not measuredOnly DeepSeek V3.2 measured
MedCode (Vals AI)Not measured34.4%Only MiniMax M2.7 measured
MMLU Pro (Artificial Analysis run)86.2%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: science14461416DeepSeek V3.2
LMArena Text: medicine and healthcare14401409DeepSeek V3.2
LMArena Text: legal and government14251403DeepSeek V3.2
LMArena Text: business and finance14101407DeepSeek V3.2
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for DeepSeek V3.2 and MiniMax M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
Design Arena: websites11751243MiniMax M2.7
Design Arena: UI components11461210MiniMax M2.7
Design Arena: game dev11311209MiniMax M2.7
Design Arena: data viz11581233MiniMax M2.7
Design Arena: 3D11321195MiniMax M2.7
Design Arena: all code categories11631233MiniMax M2.7
Design Arena: SVG10321137MiniMax M2.7
Design Arena: ASCII art10831136MiniMax M2.7
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index172
General benchmarks for DeepSeek V3.2 and MiniMax M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
MedScribe (Vals AI)Not measured79.9%Only MiniMax M2.7 measured
IFBench60.7%75.7%MiniMax M2.7
Long context reasoning (AA-LCR)73.3%78.3%MiniMax M2.7
DTBench85.6%Not measuredOnly DeepSeek V3.2 measured
LMCA28.8%Not measuredOnly DeepSeek V3.2 measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
ExploitBenchNot measured13.3%Only MiniMax M2.7 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251405DeepSeek V3.2
LMArena Text: instruction following14131405DeepSeek V3.2
LMArena Text: creative writing14001354DeepSeek V3.2
LMArena Text: English14391426DeepSeek V3.2
LMArena Text: non-English14091382DeepSeek V3.2
LMArena Text: Chinese14551442DeepSeek V3.2
LMArena Text: German14131398DeepSeek V3.2
LMArena Text: Japanese13741260DeepSeek V3.2
LMArena Text: Korean13701314DeepSeek V3.2
LMArena Text: French14291424DeepSeek V3.2
LMArena Text: Spanish14241402DeepSeek V3.2
LMArena Text: Russian14241383DeepSeek V3.2
LMArena Text: Polish14191387DeepSeek V3.2
LMArena Text: multi-turn14271412DeepSeek V3.2
LMArena Text: longer queries14281418DeepSeek V3.2
LMArena Text: writing and language14071376DeepSeek V3.2
LMArena Text: entertainment and media13951360DeepSeek V3.2
Neither model has a result on the other 21 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 M2.7
BenchmarkDeepSeek V3.2MiniMax M2.7Leader
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$0.0007Fits in one request
MiniMax M2.7$0.0009Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
MiniMax M2.7$0.019Fits in one request

DeepSeek V3.2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
MiniMax M2.7$0.072Exceeds the context window

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 M2.7
SpecificationDeepSeek V3.2MiniMax M2.7
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025March 18, 2026
Context window164K205K
Input $/Mtok$0.29$0.30
Output $/Mtok$0.88$1.20
Coding index30.036.2
Independent measurements behind it33
Cost per solved task$0.99$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than MiniMax M2.7 for coding?

Pick MiniMax M2.7 for coding: it scores 36.2 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 1.4x cheaper ($0.88 vs $1.20 per million) and work measured by LiveCodeBench (Vals AI) or LMArena Text: software and IT, where it leads.

Which is cheaper, DeepSeek V3.2 or MiniMax M2.7?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and MiniMax M2.7 $0.64.

Which has the bigger context window, DeepSeek V3.2 or MiniMax M2.7?

MiniMax M2.7, with 205K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs MiniMax M2.7 comparison based on?

59 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and MiniMax M2.7's on 3. 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-m2-7" title="DeepSeek V3.2 vs MiniMax M2.7, 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-m2-7">LLMBenchmark.ai, DeepSeek V3.2 vs MiniMax M2.7</a></p>