Enter opens the highlighted result. Esc closes.

MiniMax M2.5 vs Qwen3 30B A3B

MiniMax M2.5 leads Qwen3 30B A3B on the Artificial Analysis Intelligence Index, 22.8 to 7.6, and Qwen3 30B A3B costs 2.4x less per output token ($0.50 vs $1.20 per million). Updated October 22, 2026; 41 benchmarks have a result for both.

Replace MiniMax M2.5 Replace Qwen3 30B A3B
MiniMax M2.5MiniMax
Coding
37.2
Overall
37.3
Output $/M
$1.20
39
Qwen3 30B A3BQwen
Coding
No data
Overall
38.2
Output $/M
$0.50
2
vs boards won of 41 shared

MiniMax M2.5 or Qwen3 30B A3B: which to pick

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Qwen3 30B A3B has none, so the two cannot be ranked on coding.

Pick Qwen3 30B A3B for output tokens 2.4x cheaper ($0.50 vs $1.20 per million) and work measured by LMArena Text: Japanese or LMArena Text: Korean, where it leads.

Model AMiniMax M2.5MiniMax37.2/1003 independent benchmarks$0.62 per solved taskModel BQwen3 30B A3BQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
41
MiniMax M2.5 only
30
Qwen3 30B A3B only
12
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 30B A3B not benchmarked.
Widest category
Agentic work, 69.3 points apart on average over 1 shared benchmark.
Widest single gap
Long context reasoning (AA-LCR): MiniMax M2.5 73.3% against Qwen3 30B A3B 0.0%, 73.3 points apart on a 0 to 100 scale.
Output price
MiniMax M2.5 $1.20 against Qwen3 30B A3B $0.50 per million output tokens, 2.4x apart.
Context window
MiniMax M2.5 takes 205K tokens, Qwen3 30B A3B 41K.

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 30B A3BTies
Coding30
Intelligence20
Agentic work10
Reasoning50
Math20
Knowledge40
Web design50
General172
All shared boards392
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for MiniMax M2.5 and Qwen3 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
SWE-bench Verified75.8%Not measuredOnly MiniMax M2.5 measured
SWE-bench Multilingual68.3%Not measuredOnly MiniMax M2.5 measured
LMArena WebDev1386Not measuredOnly MiniMax M2.5 measured
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
LiveCodeBench (Artificial Analysis run)Not measured50.6%Only Qwen3 30B A3B measured
Terminal-Bench Hard (Artificial Analysis run)34.8%6.8%MiniMax M2.5
Terminal-Bench42.7%Not measuredOnly MiniMax M2.5 measured
WeirdMLNot measured29.8%Only Qwen3 30B A3B measured
ALE-Bench618.2Not measuredOnly MiniMax M2.5 measured
LMArena Text: coding13801337MiniMax M2.5
LMArena Text: software and IT13831340MiniMax M2.5
LMArena WebDev: React1374Not measuredOnly MiniMax M2.5 measured
LMArena WebDev: HTML1414Not measuredOnly MiniMax M2.5 measured
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 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for MiniMax M2.5 and Qwen3 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
AA Intelligence Index22.87.6MiniMax M2.5
Epoch Capabilities Index146.6137.3MiniMax M2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for MiniMax M2.5 and Qwen3 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
τ²-Bench Telecom95.3%26.0%MiniMax M2.5
Vending-Bench 2-$23Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for MiniMax M2.5 and Qwen3 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
GPQA Diamond82.1%Not measuredOnly MiniMax M2.5 measured
GPQA Diamond (Artificial Analysis run)84.8%61.6%MiniMax M2.5
Humanity's Last Exam (Artificial Analysis run)20.5%6.2%MiniMax M2.5
GPQA Diamond (Epoch AI run)Not measured61.7%Only Qwen3 30B A3B measured
ARC-AGI63.7%Not measuredOnly MiniMax M2.5 measured
ARC-AGI-24.9%Not measuredOnly MiniMax M2.5 measured
LMArena Text: hard prompts13721314MiniMax M2.5
LMArena Text: expert13781314MiniMax M2.5
LMArena Text: hard prompts in English13841329MiniMax M2.5
Kagi LLM Benchmark55.2%Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for MiniMax M2.5 and Qwen3 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
AIME88.8%Not measuredOnly MiniMax M2.5 measured
AA Math IndexNot measured72.3Only Qwen3 30B A3B measured
AIME 2025 (Artificial Analysis run)Not measured72.3%Only Qwen3 30B A3B measured
OTIS Mock AIMENot measured62.8%Only Qwen3 30B A3B measured
ProofBench4.0%Not measuredOnly MiniMax M2.5 measured
LMArena Text: math13781355MiniMax M2.5
LMArena Text: mathematical work13781363MiniMax M2.5
MathArenaNot measured9.4%Only Qwen3 30B A3B measured
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for MiniMax M2.5 and Qwen3 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
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
MMLU Pro (Artificial Analysis run)Not measured77.7%Only Qwen3 30B A3B measured
LMArena Text: science13691321MiniMax M2.5
LMArena Text: medicine and healthcare13571318MiniMax M2.5
LMArena Text: legal and government13661314MiniMax M2.5
LMArena Text: business and finance13561309MiniMax M2.5
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index50
Web design benchmarks for MiniMax M2.5 and Qwen3 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
Design Arena: websites1222954MiniMax M2.5
Design Arena: UI components1170943MiniMax M2.5
Design Arena: game dev1176898MiniMax M2.5
Design Arena: data viz1172967MiniMax M2.5
Design Arena: 3D1170Not measuredOnly MiniMax M2.5 measured
Design Arena: all code categories1207941MiniMax M2.5
Design Arena: SVG1150Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index172
General benchmarks for MiniMax M2.5 and Qwen3 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
IFBench71.6%41.5%MiniMax M2.5
Long context reasoning (AA-LCR)73.3%0.0%MiniMax M2.5
DTBenchNot measured60.3%Only Qwen3 30B A3B measured
LMCANot measured15.8%Only Qwen3 30B A3B measured
Fiction.LiveBenchNot measured40.6%Only Qwen3 30B A3B measured
Creative writing (Lech Mazur)Not measured75.3%Only Qwen3 30B A3B measured
CL-bench11.4%Not measuredOnly MiniMax M2.5 measured
CL-bench Life6.3%Not measuredOnly MiniMax M2.5 measured
LMArena Text13591317MiniMax M2.5
LMArena Text: instruction following13531283MiniMax M2.5
LMArena Text: creative writing13311271MiniMax M2.5
LMArena Text: English13801335MiniMax M2.5
LMArena Text: non-English13381295MiniMax M2.5
LMArena Text: Chinese13931347MiniMax M2.5
LMArena Text: German13611307MiniMax M2.5
LMArena Text: Japanese11711254Qwen3 30B A3B
LMArena Text: Korean12331261Qwen3 30B A3B
LMArena Text: French13631352MiniMax M2.5
LMArena Text: Spanish13531317MiniMax M2.5
LMArena Text: Russian13591291MiniMax M2.5
LMArena Text: Polish13341299MiniMax M2.5
LMArena Text: multi-turn13641307MiniMax M2.5
LMArena Text: longer queries13661312MiniMax M2.5
LMArena Text: writing and language13451290MiniMax M2.5
LMArena Text: entertainment and media13291258MiniMax M2.5
Neither model has a result on the other 23 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 30B A3B
BenchmarkMiniMax M2.5Qwen3 30B A3BLeader
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 30B A3B$0.0004Fits in one request

Qwen3 30B A3B costs less

Repository review

50K input + 3K output tokens

MiniMax M2.5$0.019Fits in one request
Qwen3 30B A3B$0.0075Exceeds the context window

Qwen3 30B A3B costs less

Agent loop

200K input + 10K output tokens

MiniMax M2.5$0.072Exceeds the context window
Qwen3 30B A3B$0.029Exceeds the context window

Qwen3 30B A3B 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 30B A3B
SpecificationMiniMax M2.5Qwen3 30B A3B
MakerMiniMaxQwen
WeightsOpen weightsOpen weights
ReleasedFebruary 12, 2026April 28, 2025
Context window205K41K
Input $/Mtok$0.30$0.12
Output $/Mtok$1.20$0.50
Coding index37.2Not benchmarked
Independent measurements behind it30
Cost per solved task$0.62Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2.5 better than Qwen3 30B A3B for coding?

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Qwen3 30B A3B has none, so the two cannot be ranked on coding. Pick Qwen3 30B A3B for output tokens 2.4x cheaper ($0.50 vs $1.20 per million) and work measured by LMArena Text: Japanese or LMArena Text: Korean, where it leads.

Which is cheaper, MiniMax M2.5 or Qwen3 30B A3B?

MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Qwen3 30B A3B costs $0.12 and $0.50. Cost per solved task is known for MiniMax M2.5 only.

Which has the bigger context window, MiniMax M2.5 or Qwen3 30B A3B?

MiniMax M2.5, with 205K tokens against 41K.

How many benchmarks is the MiniMax M2.5 vs Qwen3 30B A3B comparison based on?

41 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and Qwen3 30B A3B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next