Enter opens the highlighted result. Esc closes.

MiniMax M2.5 vs Qwen3.5 397B A17B

MiniMax M2.5 leads Qwen3.5 397B A17B on the Artificial Analysis Intelligence Index, 22.8 to 21.4, and MiniMax M2.5 costs 1.9x less per output token ($1.20 vs $2.34 per million). Updated October 23, 2026; 47 benchmarks have a result for both.

Replace MiniMax M2.5 Replace Qwen3.5 397B A17B
MiniMax M2.5MiniMax
Coding
37.2
Overall
37.3
Output $/M
$1.20
8
Qwen3.5 397B A17BQwen
Coding
No data
Overall
57.2
Output $/M
$2.34
39
vs boards won of 47 shared

MiniMax M2.5 or Qwen3.5 397B A17B: which to pick

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding.

Pick Qwen3.5 397B A17B for a larger context window (262K against 205K tokens) and work measured by LMArena WebDev or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AMiniMax M2.5MiniMax37.2/1003 independent benchmarks$0.62 per solved taskModel BQwen3.5 397B A17BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
47
MiniMax M2.5 only
24
Qwen3.5 397B A17B only
19
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 M2.5 37.2 from 3 benchmarks, Qwen3.5 397B A17B not benchmarked.
Widest category
General, 15.0 points apart on average over 19 shared benchmarks.
Widest single gap
LMArena Text: Japanese: MiniMax M2.5 1171 against Qwen3.5 397B A17B 1430, 43.1 points apart on a 0 to 100 scale.
Output price
MiniMax M2.5 $1.20 against Qwen3.5 397B A17B $2.34 per million output tokens, 1.9x apart.
Context window
MiniMax M2.5 takes 205K tokens, Qwen3.5 397B A17B 262K.

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 M2.5BarsQwen3.5 397B A17BTies
Coding16
Intelligence11
Agentic work01
Reasoning05
Math02
Knowledge04
Web design61
General019
All shared boards839
CodingLike-for-likeSix of these boards feed the Vibe Coding Index16
Coding benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
SWE-bench Verified75.8%Not measuredOnly MiniMax M2.5 measured
SWE-bench Multilingual68.3%Not measuredOnly MiniMax M2.5 measured
LMArena WebDev13861400Qwen3.5 397B A17B
LiveCodeBench (Vals AI)79.2%Not measuredOnly MiniMax M2.5 measured
SWE-bench Verified (Vals AI)74.2%Not measuredOnly MiniMax M2.5 measured
Vibe Code Bench (Vals AI)14.8%Not measuredOnly MiniMax M2.5 measured
SciCodeNot measured44.8%Only Qwen3.5 397B A17B measured
Terminal-Bench Hard (Artificial Analysis run)34.8%40.9%Qwen3.5 397B A17B
Terminal-Bench42.7%Not measuredOnly MiniMax M2.5 measured
ALE-Bench618.2621.9Qwen3.5 397B A17B
LMArena Text: coding13801465Qwen3.5 397B A17B
LMArena Text: software and IT13831463Qwen3.5 397B A17B
LMArena WebDev: React13741388Qwen3.5 397B A17B
LMArena WebDev: HTML14141409MiniMax M2.5
SWE Atlas: Codebase QnA10.3%Not measuredOnly MiniMax M2.5 measured
SWE Atlas: Refactoring19.5%Not measuredOnly MiniMax M2.5 measured
SWE Atlas: Test Writing18.6%Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
AA Intelligence Index22.821.4MiniMax M2.5
Epoch Capabilities Index146.6146.8Qwen3.5 397B A17B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
τ²-Bench Telecom95.3%95.6%Qwen3.5 397B A17B
APEX-AgentsNot measured24.9%Only Qwen3.5 397B A17B measured
Vending-Bench 2-$23Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
GPQA Diamond82.1%Not measuredOnly MiniMax M2.5 measured
GPQA Diamond (Artificial Analysis run)84.8%89.3%Qwen3.5 397B A17B
Humanity's Last Exam (Artificial Analysis run)20.5%29.0%Qwen3.5 397B A17B
GPQA Diamond (Epoch AI run)Not measured86.4%Only Qwen3.5 397B A17B measured
ARC-AGI63.7%Not measuredOnly MiniMax M2.5 measured
ARC-AGI-24.9%Not measuredOnly MiniMax M2.5 measured
Mystery game puzzlesNot measured18.0%Only Qwen3.5 397B A17B measured
LMArena Text: hard prompts13721448Qwen3.5 397B A17B
LMArena Text: expert13791462Qwen3.5 397B A17B
LMArena Text: hard prompts in English13841450Qwen3.5 397B A17B
LMArena Vision: diagramsNot measured1277Only Qwen3.5 397B A17B measured
LMArena Vision: homeworkNot measured1292Only Qwen3.5 397B A17B measured
Kagi LLM Benchmark55.2%Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
AIME88.8%Not measuredOnly MiniMax M2.5 measured
OTIS Mock AIMENot measured88.9%Only Qwen3.5 397B A17B measured
FrontierMath, tiers 1 to 3Not measured31.2%Only Qwen3.5 397B A17B measured
ProofBench4.0%Not measuredOnly MiniMax M2.5 measured
LMArena Text: math13781454Qwen3.5 397B A17B
LMArena Text: mathematical work13781454Qwen3.5 397B A17B
MathArenaNot measured19.2%Only Qwen3.5 397B A17B measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
MMLU Pro80.1%Not measuredOnly MiniMax M2.5 measured
LegalBench (Vals AI)80.0%Not measuredOnly MiniMax M2.5 measured
CaseLaw (Vals AI)53.5%Not measuredOnly MiniMax M2.5 measured
CorpFin (Vals AI)59.6%Not measuredOnly MiniMax M2.5 measured
TaxEval (Vals AI)68.2%Not measuredOnly MiniMax M2.5 measured
MedQA (Vals AI)92.5%Not measuredOnly MiniMax M2.5 measured
LMArena Text: science13691457Qwen3.5 397B A17B
LMArena Text: medicine and healthcare13571455Qwen3.5 397B A17B
LMArena Text: legal and government13661441Qwen3.5 397B A17B
LMArena Text: business and finance13561435Qwen3.5 397B A17B
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index61
Web design benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
Design Arena: websites12221190MiniMax M2.5
Design Arena: UI components11701161MiniMax M2.5
Design Arena: game dev11761140MiniMax M2.5
Design Arena: data viz11721175Qwen3.5 397B A17B
Design Arena: 3D11701162MiniMax M2.5
Design Arena: all code categories12071179MiniMax M2.5
Design Arena: SVG11501139MiniMax M2.5
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
General benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
IFBench71.6%78.8%Qwen3.5 397B A17B
Long context reasoning (AA-LCR)73.3%77.3%Qwen3.5 397B A17B
DTBenchNot measured87.5%Only Qwen3.5 397B A17B measured
LMCANot measured37.9%Only Qwen3.5 397B A17B measured
CL-bench11.4%Not measuredOnly MiniMax M2.5 measured
CL-bench Life6.3%Not measuredOnly MiniMax M2.5 measured
LMArena Text13591438Qwen3.5 397B A17B
LMArena Text: instruction following13531423Qwen3.5 397B A17B
LMArena Text: creative writing13311402Qwen3.5 397B A17B
LMArena VisionNot measured1262Only Qwen3.5 397B A17B measured
LMArena Text: English13801443Qwen3.5 397B A17B
LMArena Text: non-English13381430Qwen3.5 397B A17B
LMArena Text: Chinese13931499Qwen3.5 397B A17B
LMArena Text: German13611444Qwen3.5 397B A17B
LMArena Text: Japanese11711430Qwen3.5 397B A17B
LMArena Text: Korean12331385Qwen3.5 397B A17B
LMArena Text: French13631462Qwen3.5 397B A17B
LMArena Text: Spanish13531441Qwen3.5 397B A17B
LMArena Text: Russian13591430Qwen3.5 397B A17B
LMArena Text: Polish13341448Qwen3.5 397B A17B
LMArena Text: multi-turn13641447Qwen3.5 397B A17B
LMArena Text: longer queries13661441Qwen3.5 397B A17B
LMArena Text: writing and language13451416Qwen3.5 397B A17B
LMArena Text: entertainment and media13291399Qwen3.5 397B A17B
LMArena Vision: EnglishNot measured1268Only Qwen3.5 397B A17B measured
LMArena Vision: ChineseNot measured1314Only Qwen3.5 397B A17B measured
LMArena Vision: reading textNot measured1271Only Qwen3.5 397B A17B measured
LMArena Vision: humorNot measured1262Only Qwen3.5 397B A17B measured
LMArena Vision: captioningNot measured1230Only Qwen3.5 397B A17B measured
LMArena Vision: recognizing thingsNot measured1265Only Qwen3.5 397B A17B measured
LMArena Vision: creative writingNot measured1260Only Qwen3.5 397B A17B measured
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2.5 and Qwen3.5 397B A17B
BenchmarkMiniMax M2.5Qwen3.5 397B A17BLeader
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 M2.5$0.0009Fits in one request
Qwen3.5 397B A17B$0.0016Fits in one request

MiniMax M2.5 costs less

Repository review

50K input + 3K output tokens

MiniMax M2.5$0.019Fits in one request
Qwen3.5 397B A17B$0.027Fits in one request

MiniMax M2.5 costs less

Agent loop

200K input + 10K output tokens

MiniMax M2.5$0.072Exceeds the context window
Qwen3.5 397B A17B$0.101Fits in one request

MiniMax M2.5 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 M2.5 and Qwen3.5 397B A17B
SpecificationMiniMax M2.5Qwen3.5 397B A17B
MakerMiniMaxQwen
WeightsOpen weightsOpen weights
ReleasedFebruary 12, 2026February 16, 2026
Context window205K262K
Input $/Mtok$0.30$0.39
Output $/Mtok$1.20$2.34
Coding index37.2Not benchmarked
Independent measurements behind it31
Cost per solved task$0.62Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2.5 better than Qwen3.5 397B A17B for coding?

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Qwen3.5 397B A17B has none, so the two cannot be ranked on coding. Pick Qwen3.5 397B A17B for a larger context window (262K against 205K tokens) and work measured by LMArena WebDev or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, MiniMax M2.5 or Qwen3.5 397B A17B?

MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for MiniMax M2.5 only.

Which has the bigger context window, MiniMax M2.5 or Qwen3.5 397B A17B?

Qwen3.5 397B A17B, with 262K tokens against 205K.

How many benchmarks is the MiniMax M2.5 vs Qwen3.5 397B A17B comparison based on?

47 benchmarks have a result for both models as of October 23, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next