Enter opens the highlighted result. Esc closes.

MiniMax M2.7 vs Qwen3.6 Plus

Qwen3.6 Plus leads MiniMax M2.7 on coding, 44.1 to 36.2 on the Vibe Coding Index, and MiniMax M2.7 costs 1.6x less per output token ($1.20 vs $1.95 per million). Updated October 22, 2026; 68 benchmarks have a result for both.

Replace MiniMax M2.7 Replace Qwen3.6 Plus
MiniMax M2.7MiniMax
Coding
36.2
Overall
44.5
Output $/M
$1.20
7
Qwen3.6 PlusQwen
Coding
44.1
Overall
56.2
Output $/M
$1.95
59
vs boards won of 68 shared, 2 tied

MiniMax M2.7 or Qwen3.6 Plus: which to pick

Pick Qwen3.6 Plus for coding: it scores 44.1 on the Vibe Coding Index against 36.2 for MiniMax M2.7.

Pick MiniMax M2.7 for output tokens 1.6x cheaper ($1.20 vs $1.95 per million) and a lower cost per solved task ($0.64 against $1.19).

Model AMiniMax M2.7MiniMax36.2/1003 independent benchmarks$0.64 per solved taskModel BQwen3.6 PlusQwen44.1/1003 independent benchmarks$1.19 per solved task
Shared results
68
MiniMax M2.7 only
6
Qwen3.6 Plus 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
MiniMax M2.7 36.2 from 3 benchmarks, Qwen3.6 Plus 44.1 from 3 benchmarks.
Widest category
Agentic work, 7.1 points apart on average over 5 shared benchmarks.
Widest single gap
LMArena Text: Japanese: MiniMax M2.7 1260 against Qwen3.6 Plus 1390, 21.6 points apart on a 0 to 100 scale.
Output price
MiniMax M2.7 $1.20 against Qwen3.6 Plus $1.95 per million output tokens, 1.6x apart.
Context window
MiniMax M2.7 takes 205K tokens, Qwen3.6 Plus 1M.

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
CategoryMiniMax M2.7BarsQwen3.6 PlusTies
Coding1121 tie
Intelligence02
Agentic work05
Reasoning15
Math03
Knowledge19
Web design26
General2171 tie
All shared boards7592 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index112
Coding benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
LMArena WebDev13991461Qwen3.6 Plus
AA Coding Index52.654.5Qwen3.6 Plus
LiveCodeBench (Vals AI)79.9%86.0%Qwen3.6 Plus
SWE-bench Verified (Vals AI)73.8%73.4%MiniMax M2.7
Vibe Code Bench (Vals AI)11.9%25.6%Qwen3.6 Plus
Code migration (Vals AI)8.7%11.1%Qwen3.6 Plus
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)48.7%53.2%Qwen3.6 Plus
SciCode50.1%Not measuredOnly MiniMax M2.7 measured
Terminal-Bench Hard (Artificial Analysis run)39.4%43.9%Qwen3.6 Plus
Terminal-Bench45.1%Not measuredOnly MiniMax M2.7 measured
WeirdML37.0%Not measuredOnly MiniMax M2.7 measured
ALE-Bench599.3670.1Qwen3.6 Plus
LMArena Text: coding14541467Qwen3.6 Plus
LMArena Text: software and IT14461462Qwen3.6 Plus
LMArena WebDev: React13881454Qwen3.6 Plus
LMArena WebDev: HTML14011463Qwen3.6 Plus
LMArena WebDev: from an imageNot measured1472Only Qwen3.6 Plus measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
AA Intelligence Index22.827.0Qwen3.6 Plus
Epoch Capabilities Index145.8147.3Qwen3.6 Plus
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
AA Agentic Index15.3Not measuredOnly MiniMax M2.7 measured
Finance Agent (Vals AI)27.9%40.9%Qwen3.6 Plus
Tax Agent Bench (Vals AI)6.9%7.7%Qwen3.6 Plus
Legal Research Bench (Vals AI)10.6%14.9%Qwen3.6 Plus
Excel Modeling Benchmark (Vals AI)28.4%32.9%Qwen3.6 Plus
τ²-Bench Telecom84.8%97.7%Qwen3.6 Plus
Vending-Bench 2Not measured$5,115Only Qwen3.6 Plus measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
Reasoning benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
GPQA Diamond86.6%87.4%Qwen3.6 Plus
MMMU Pro (Vals AI)Not measured84.2%Only Qwen3.6 Plus measured
GPQA Diamond (Artificial Analysis run)87.4%88.2%Qwen3.6 Plus
Humanity's Last Exam (Artificial Analysis run)29.6%27.8%MiniMax M2.7
GPQA Diamond (Epoch AI run)Not measured88.4%Only Qwen3.6 Plus measured
Chess puzzlesNot measured14.0%Only Qwen3.6 Plus measured
Mystery game puzzlesNot measured12.0%Only Qwen3.6 Plus measured
LMArena Text: hard prompts14221448Qwen3.6 Plus
LMArena Text: expert14431454Qwen3.6 Plus
LMArena Text: hard prompts in English14411455Qwen3.6 Plus
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
AIME91.0%94.6%Qwen3.6 Plus
OTIS Mock AIMENot measured93.3%Only Qwen3.6 Plus measured
FrontierMath, tiers 1 to 3Not measured38.2%Only Qwen3.6 Plus measured
ProofBench3.0%Not measuredOnly MiniMax M2.7 measured
LMArena Text: math14211449Qwen3.6 Plus
LMArena Text: mathematical work14371448Qwen3.6 Plus
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
MMLU Pro80.4%87.7%Qwen3.6 Plus
LegalBench (Vals AI)84.0%84.2%Qwen3.6 Plus
CaseLaw (Vals AI)60.9%51.5%MiniMax M2.7
CorpFin (Vals AI)61.2%61.9%Qwen3.6 Plus
TaxEval (Vals AI)66.6%74.7%Qwen3.6 Plus
MortgageTax (Vals AI)Not measured68.0%Only Qwen3.6 Plus measured
MedCode (Vals AI)34.4%36.9%Qwen3.6 Plus
SimpleQA VerifiedNot measured44.1%Only Qwen3.6 Plus measured
LMArena Text: science14161439Qwen3.6 Plus
LMArena Text: medicine and healthcare14091442Qwen3.6 Plus
LMArena Text: legal and government14031437Qwen3.6 Plus
LMArena Text: business and finance14071430Qwen3.6 Plus
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index26
Web design benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
Design Arena: websites12421243Qwen3.6 Plus
Design Arena: UI components12071230Qwen3.6 Plus
Design Arena: game dev12091211Qwen3.6 Plus
Design Arena: data viz12331228MiniMax M2.7
Design Arena: 3D11941202Qwen3.6 Plus
Design Arena: all code categories12331235Qwen3.6 Plus
Design Arena: SVG11371160Qwen3.6 Plus
Design Arena: ASCII art11361113MiniMax M2.7
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index217
General benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
SAGE (Vals AI)Not measured44.9%Only Qwen3.6 Plus measured
MedScribe (Vals AI)79.9%77.0%MiniMax M2.7
Vals Multimodal IndexNot measured51.5%Only Qwen3.6 Plus measured
IFBench75.7%75.2%MiniMax M2.7
Long context reasoning (AA-LCR)78.3%78.3%Tie
DTBenchNot measured81.9%Only Qwen3.6 Plus measured
LMCANot measured33.1%Only Qwen3.6 Plus measured
CL-benchNot measured20.3%Only Qwen3.6 Plus measured
ExploitBench13.3%Not measuredOnly MiniMax M2.7 measured
LMArena Text14051436Qwen3.6 Plus
LMArena Text: instruction following14051424Qwen3.6 Plus
LMArena Text: creative writing13541404Qwen3.6 Plus
LMArena Text: English14261445Qwen3.6 Plus
LMArena Text: non-English13821424Qwen3.6 Plus
LMArena Text: Chinese14421477Qwen3.6 Plus
LMArena Text: German13981451Qwen3.6 Plus
LMArena Text: Japanese12601390Qwen3.6 Plus
LMArena Text: Korean13141379Qwen3.6 Plus
LMArena Text: French14241455Qwen3.6 Plus
LMArena Text: Spanish14021432Qwen3.6 Plus
LMArena Text: Russian13831434Qwen3.6 Plus
LMArena Text: Polish13871433Qwen3.6 Plus
LMArena Text: multi-turn14121438Qwen3.6 Plus
LMArena Text: longer queries14181439Qwen3.6 Plus
LMArena Text: writing and language13761418Qwen3.6 Plus
LMArena Text: entertainment and media13601402Qwen3.6 Plus
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2.7 and Qwen3.6 Plus
BenchmarkMiniMax M2.7Qwen3.6 PlusLeader
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

MiniMax M2.7$0.0009Fits in one request
Qwen3.6 Plus$0.0013Fits in one request

MiniMax M2.7 costs less

Repository review

50K input + 3K output tokens

MiniMax M2.7$0.019Fits in one request
Qwen3.6 Plus$0.022Fits in one request

MiniMax M2.7 costs less

Agent loop

200K input + 10K output tokens

MiniMax M2.7$0.072Exceeds the context window
Qwen3.6 Plus$0.085Fits in one request

MiniMax M2.7 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 MiniMax M2.7 and Qwen3.6 Plus
SpecificationMiniMax M2.7Qwen3.6 Plus
MakerMiniMaxQwen
WeightsOpen weightsNo public weights listed
ReleasedMarch 18, 2026April 2, 2026
Context window205K1M
Input $/Mtok$0.30$0.325
Output $/Mtok$1.20$1.95
Coding index36.244.1
Independent measurements behind it33
Cost per solved task$0.64$1.19
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2.7 better than Qwen3.6 Plus for coding?

Pick Qwen3.6 Plus for coding: it scores 44.1 on the Vibe Coding Index against 36.2 for MiniMax M2.7. Pick MiniMax M2.7 for output tokens 1.6x cheaper ($1.20 vs $1.95 per million) and a lower cost per solved task ($0.64 against $1.19).

Which is cheaper, MiniMax M2.7 or Qwen3.6 Plus?

MiniMax M2.7 costs $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.6 Plus costs $0.325 and $1.95. Per solved SWE-bench Verified task, MiniMax M2.7 costs $0.64 and Qwen3.6 Plus $1.19.

Which has the bigger context window, MiniMax M2.7 or Qwen3.6 Plus?

Qwen3.6 Plus, with 1M tokens against 205K.

How many benchmarks is the MiniMax M2.7 vs Qwen3.6 Plus comparison based on?

68 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.7's coding index rests on 3 independent benchmarks and Qwen3.6 Plus'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/minimax-minimax-m2-7-vs-qwen3-6-plus" title="MiniMax M2.7 vs Qwen3.6 Plus, 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/minimax-minimax-m2-7-vs-qwen3-6-plus">LLMBenchmark.ai, MiniMax M2.7 vs Qwen3.6 Plus</a></p>