Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 vs MiniMax M2

MiniMax M2 leads DeepSeek V3.1 on the Artificial Analysis Intelligence Index, 18.6 to 13.7, and MiniMax M2 costs 1.5x less per output token ($1.02 vs $1.50 per million). Updated October 23, 2026; 9 benchmarks have a result for both.

Replace DeepSeek V3.1 Replace MiniMax M2
DeepSeek V3.1DeepSeek
Coding
No data
Overall
No data
Output $/M
$1.50
0
MiniMax M2MiniMax
Coding
No data
Overall
No data
Output $/M
$1.02
9
vs boards won of 9 shared

DeepSeek V3.1 or MiniMax M2: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick DeepSeek V3.1 for work measured by AA Intelligence Index or Kagi LLM Benchmark, where it leads.

Model ADeepSeek V3.1DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMiniMax M2MiniMaxNot benchmarked1 independent benchmark$0.702 per solved task
Shared results
9
DeepSeek V3.1 only
2
MiniMax M2 only
41
Like-for-like categories
3 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 V3.1 not benchmarked, MiniMax M2 not benchmarked.
Widest category
Web design, 5.8 points apart on average over 7 shared benchmarks.
Widest single gap
Design Arena: SVG: DeepSeek V3.1 967 against MiniMax M2 1100, 16.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 $1.50 against MiniMax M2 $1.02 per million output tokens, 1.5x apart.
Context window
DeepSeek V3.1 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 V3.1BarsMiniMax M2Ties
Intelligence01
Reasoning01
Web design07
All shared boards09
CodingDirectional onlySix of these boards feed the Vibe Coding Index8 boards, none shared
Coding benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax M2Leader
SWE-bench VerifiedNot measured61.0%Only MiniMax M2 measured
LMArena WebDevNot measured1297Only MiniMax M2 measured
LiveCodeBench (Artificial Analysis run)Not measured82.6%Only MiniMax M2 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured25.8%Only MiniMax M2 measured
Terminal-BenchNot measured30.0%Only MiniMax M2 measured
LMArena Text: codingNot measured1371Only MiniMax M2 measured
LMArena Text: software and ITNot measured1373Only MiniMax M2 measured
LMArena WebDev: HTMLNot measured1306Only MiniMax M2 measured
Neither model has a result on the other 35 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax M2Leader
AA Intelligence Index13.718.6MiniMax M2
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax M2Leader
τ²-Bench TelecomNot measured86.8%Only MiniMax M2 measured
Vending-Bench 2Not measured$161Only MiniMax M2 measured
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
Reasoning benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax M2Leader
GPQA Diamond (Artificial Analysis run)Not measured77.7%Only MiniMax M2 measured
Humanity's Last Exam (Artificial Analysis run)Not measured13.7%Only MiniMax M2 measured
LMArena Text: hard promptsNot measured1357Only MiniMax M2 measured
LMArena Text: expertNot measured1338Only MiniMax M2 measured
LMArena Text: hard prompts in EnglishNot measured1376Only MiniMax M2 measured
Kagi LLM Benchmark53.2%57.8%MiniMax M2
Neither model has a result on the other 17 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax M2Leader
AA Math IndexNot measured78.3Only MiniMax M2 measured
AIME 2025 (Artificial Analysis run)Not measured78.3%Only MiniMax M2 measured
LMArena Text: mathNot measured1351Only MiniMax M2 measured
LMArena Text: mathematical workNot measured1368Only MiniMax M2 measured
Neither model has a result on the other 10 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Knowledge benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax M2Leader
MMLU Pro (Artificial Analysis run)Not measured82.0%Only MiniMax M2 measured
LMArena Text: scienceNot measured1349Only MiniMax M2 measured
LMArena Text: medicine and healthcareNot measured1367Only MiniMax M2 measured
LMArena Text: legal and governmentNot measured1349Only MiniMax M2 measured
LMArena Text: business and financeNot measured1336Only MiniMax M2 measured
Neither model has a result on the other 15 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax M2Leader
Design Arena: websites11221143MiniMax M2
Design Arena: UI components10831134MiniMax M2
Design Arena: game dev10841118MiniMax M2
Design Arena: data viz10961140MiniMax M2
Design Arena: 3D10771098MiniMax M2
Design Arena: all code categories11121135MiniMax M2
Design Arena: SVG9671100MiniMax M2
Neither model has a result on the other 2 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
General benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax M2Leader
IFBenchNot measured72.3%Only MiniMax M2 measured
Long context reasoning (AA-LCR)Not measured64.3%Only MiniMax M2 measured
DTBench82.7%Not measuredOnly DeepSeek V3.1 measured
LMCA24.3%Not measuredOnly DeepSeek V3.1 measured
LMArena TextNot measured1340Only MiniMax M2 measured
LMArena Text: instruction followingNot measured1329Only MiniMax M2 measured
LMArena Text: creative writingNot measured1287Only MiniMax M2 measured
LMArena Text: EnglishNot measured1364Only MiniMax M2 measured
LMArena Text: non-EnglishNot measured1313Only MiniMax M2 measured
LMArena Text: ChineseNot measured1366Only MiniMax M2 measured
LMArena Text: GermanNot measured1354Only MiniMax M2 measured
LMArena Text: FrenchNot measured1336Only MiniMax M2 measured
LMArena Text: SpanishNot measured1326Only MiniMax M2 measured
LMArena Text: RussianNot measured1330Only MiniMax M2 measured
LMArena Text: PolishNot measured1311Only MiniMax M2 measured
LMArena Text: multi-turnNot measured1361Only MiniMax M2 measured
LMArena Text: longer queriesNot measured1331Only MiniMax M2 measured
LMArena Text: writing and languageNot measured1295Only MiniMax M2 measured
LMArena Text: entertainment and mediaNot measured1298Only MiniMax M2 measured
Neither model has a result on the other 29 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.1 and MiniMax M2
BenchmarkDeepSeek V3.1MiniMax 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 V3.1$0.0013Fits in one request
MiniMax M2$0.0008Fits in one request

MiniMax M2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1$0.032Fits in one request
MiniMax M2$0.016Fits in one request

MiniMax M2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1$0.125Exceeds 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 V3.1 and MiniMax M2
SpecificationDeepSeek V3.1MiniMax M2
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedAugust 21, 2025October 23, 2025
Context window164K205K
Input $/Mtok$0.55$0.255
Output $/Mtok$1.50$1.02
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computable$0.702
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 better than MiniMax M2 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 for work measured by AA Intelligence Index or Kagi LLM Benchmark, where it leads.

Which is cheaper, DeepSeek V3.1 or MiniMax M2?

DeepSeek V3.1 costs $0.55 per million input tokens and $1.50 per million output tokens; MiniMax M2 costs $0.255 and $1.02. Cost per solved task is known for MiniMax M2 only.

Which has the bigger context window, DeepSeek V3.1 or MiniMax M2?

MiniMax M2, with 205K tokens against 164K.

How many benchmarks is the DeepSeek V3.1 vs MiniMax M2 comparison based on?

9 benchmarks have a result for both models as of October 23, 2026. DeepSeek V3.1's coding index rests on 0 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