Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs MiniMax M2

DeepSeek V3.2 leads MiniMax M2 on the Artificial Analysis Intelligence Index, 21.5 to 18.6, at about the same output price ($0.88 vs $1.02 per million). Updated October 22, 2026; 49 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace MiniMax M2
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
47
MiniMax M2MiniMax
Coding
No data
Overall
No data
Output $/M
$1.02
2
vs boards won of 49 shared

DeepSeek V3.2 or MiniMax M2: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; MiniMax M2 has none, so the two cannot be ranked on coding.

Pick MiniMax M2 for a lower cost per solved task ($0.702 against $0.99) and a larger context window (205K against 164K tokens).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BMiniMax M2MiniMaxNot benchmarked1 independent benchmark$0.702 per solved task
Shared results
49
DeepSeek V3.2 only
27
MiniMax M2 only
1
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 not benchmarked.
Widest category
General, 14.6 points apart on average over 17 shared benchmarks.
Widest single gap
LMArena Text: creative writing: DeepSeek V3.2 1400 against MiniMax M2 1286, 18.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against MiniMax M2 $1.02 per million output tokens, 1.2x apart.
Context window
DeepSeek V3.2 takes 164K tokens, MiniMax M2 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 M2Ties
Coding80
Intelligence10
Agentic work20
Reasoning50
Math40
Knowledge50
Web design61
General161
All shared boards472
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
Coding benchmarks for DeepSeek V3.2 and MiniMax M2
BenchmarkDeepSeek V3.2MiniMax M2Leader
SWE-bench Verified70.0%61.0%DeepSeek V3.2
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev13621297DeepSeek V3.2
AA Coding Index44.2Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Vals AI)80.7%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Verified (Vals AI)67.6%Not measuredOnly DeepSeek V3.2 measured
Vibe Code Bench (Vals AI)5.1%Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)86.2%82.6%DeepSeek V3.2
Terminal-Bench Hard (Artificial Analysis run)35.6%25.8%DeepSeek V3.2
Terminal-Bench39.6%30.0%DeepSeek V3.2
LMArena Text: coding14531371DeepSeek V3.2
LMArena Text: software and IT14491373DeepSeek V3.2
LMArena WebDev: React1350Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev: HTML13711306DeepSeek V3.2
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.2 and MiniMax M2
BenchmarkDeepSeek V3.2MiniMax M2Leader
AA Intelligence Index21.518.6DeepSeek V3.2
Epoch Capabilities Index146.1Not measuredOnly DeepSeek V3.2 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for DeepSeek V3.2 and MiniMax M2
BenchmarkDeepSeek V3.2MiniMax M2Leader
τ²-Bench Telecom90.6%86.8%DeepSeek V3.2
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034$161DeepSeek V3.2
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for DeepSeek V3.2 and MiniMax M2
BenchmarkDeepSeek V3.2MiniMax M2Leader
GPQA Diamond80.3%Not measuredOnly DeepSeek V3.2 measured
GPQA Diamond (Artificial Analysis run)84.0%77.7%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)24.6%13.7%DeepSeek V3.2
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: hard prompts14341357DeepSeek V3.2
LMArena Text: expert14361338DeepSeek V3.2
LMArena Text: hard prompts in English14461376DeepSeek V3.2
Kagi LLM BenchmarkNot measured57.8%Only MiniMax M2 measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for DeepSeek V3.2 and MiniMax M2
BenchmarkDeepSeek V3.2MiniMax M2Leader
AIME84.6%Not measuredOnly DeepSeek V3.2 measured
MGSM (Vals AI)86.0%Not measuredOnly DeepSeek V3.2 measured
AA Math Index92.078.3DeepSeek V3.2
AIME 2025 (Artificial Analysis run)92.0%78.3%DeepSeek V3.2
LMArena Text: math14351351DeepSeek V3.2
LMArena Text: mathematical work14401368DeepSeek V3.2
MathArena16.0%Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.2 and MiniMax M2
BenchmarkDeepSeek V3.2MiniMax M2Leader
MMLU Pro84.9%Not measuredOnly DeepSeek V3.2 measured
LegalBench (Vals AI)76.1%Not measuredOnly DeepSeek V3.2 measured
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%Not measuredOnly DeepSeek V3.2 measured
TaxEval (Vals AI)68.2%Not measuredOnly DeepSeek V3.2 measured
MedQA (Vals AI)93.9%Not measuredOnly DeepSeek V3.2 measured
MMLU Pro (Artificial Analysis run)86.2%82.0%DeepSeek V3.2
LMArena Text: science14461348DeepSeek V3.2
LMArena Text: medicine and healthcare14401367DeepSeek V3.2
LMArena Text: legal and government14251349DeepSeek V3.2
LMArena Text: business and finance14101336DeepSeek V3.2
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index61
Web design benchmarks for DeepSeek V3.2 and MiniMax M2
BenchmarkDeepSeek V3.2MiniMax M2Leader
Design Arena: websites11751143DeepSeek V3.2
Design Arena: UI components11461134DeepSeek V3.2
Design Arena: game dev11311118DeepSeek V3.2
Design Arena: data viz11591140DeepSeek V3.2
Design Arena: 3D11321098DeepSeek V3.2
Design Arena: all code categories11631135DeepSeek V3.2
Design Arena: SVG10311100MiniMax M2
Design Arena: ASCII art1082Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index161
General benchmarks for DeepSeek V3.2 and MiniMax M2
BenchmarkDeepSeek V3.2MiniMax M2Leader
IFBench60.7%72.3%MiniMax M2
Long context reasoning (AA-LCR)73.3%64.3%DeepSeek V3.2
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
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251340DeepSeek V3.2
LMArena Text: instruction following14131329DeepSeek V3.2
LMArena Text: creative writing14001286DeepSeek V3.2
LMArena Text: English14391364DeepSeek V3.2
LMArena Text: non-English14091313DeepSeek V3.2
LMArena Text: Chinese14551366DeepSeek V3.2
LMArena Text: German14131357DeepSeek V3.2
LMArena Text: Japanese1374Not measuredOnly DeepSeek V3.2 measured
LMArena Text: Korean1370Not measuredOnly DeepSeek V3.2 measured
LMArena Text: French14291336DeepSeek V3.2
LMArena Text: Spanish14241326DeepSeek V3.2
LMArena Text: Russian14241330DeepSeek V3.2
LMArena Text: Polish14191312DeepSeek V3.2
LMArena Text: multi-turn14271361DeepSeek V3.2
LMArena Text: longer queries14281331DeepSeek V3.2
LMArena Text: writing and language14071295DeepSeek V3.2
LMArena Text: entertainment and media13951298DeepSeek V3.2
Neither model has a result on the other 25 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
BenchmarkDeepSeek V3.2MiniMax M2Leader
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$0.0008Fits 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$0.016Fits in one request

MiniMax M2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
MiniMax M2$0.061Exceeds the context window

MiniMax M2 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
SpecificationDeepSeek V3.2MiniMax M2
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025October 23, 2025
Context window164K205K
Input $/Mtok$0.29$0.255
Output $/Mtok$0.88$1.02
Coding index30.0Not benchmarked
Independent measurements behind it31
Cost per solved task$0.99$0.702
SourceOpenRouter listingOpenRouter listing

Questions

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

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; MiniMax M2 has none, so the two cannot be ranked on coding. Pick MiniMax M2 for a lower cost per solved task ($0.702 against $0.99) and a larger context window (205K against 164K tokens).

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

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; MiniMax M2 costs $0.255 and $1.02. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and MiniMax M2 $0.702.

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

MiniMax M2, with 205K tokens against 164K.

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

49 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's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next