Enter opens the highlighted result. Esc closes.

Qwen3 30B A3B vs MiMo-V2.5-Pro

MiMo-V2.5-Pro leads Qwen3 30B A3B on the Artificial Analysis Intelligence Index, 26.0 to 7.6, and Qwen3 30B A3B costs 1.8x less per output token ($0.50 vs $0.9152 per million). Updated October 22, 2026; 42 benchmarks have a result for both.

Replace Qwen3 30B A3B Replace MiMo-V2.5-Pro
Qwen3 30B A3BQwen
Coding
No data
Overall
38.2
Output $/M
$0.50
0
MiMo-V2.5-ProXiaomi
Coding
31.6
Overall
39.3
Output $/M
$0.9152
42
vs boards won of 42 shared

Qwen3 30B A3B or MiMo-V2.5-Pro: which to pick

Only MiMo-V2.5-Pro has a coding score, 31.6 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 1.8x cheaper ($0.50 vs $0.9152 per million).

Model AQwen3 30B A3BQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BMiMo-V2.5-ProXiaomi31.6/1004 independent benchmarks$0.03 per solved task
Shared results
42
Qwen3 30B A3B only
10
MiMo-V2.5-Pro only
28
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
Qwen3 30B A3B not benchmarked, MiMo-V2.5-Pro 31.6 from 4 benchmarks.
Widest category
Agentic work, 68.1 points apart on average over 1 shared benchmark.
Widest single gap
Long context reasoning (AA-LCR): Qwen3 30B A3B 0.0% against MiMo-V2.5-Pro 79.7%, 79.7 points apart on a 0 to 100 scale.
Output price
Qwen3 30B A3B $0.50 against MiMo-V2.5-Pro $0.9152 per million output tokens, 1.8x apart.
Context window
Qwen3 30B A3B takes 41K tokens, MiMo-V2.5-Pro 1.05M.

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
CategoryQwen3 30B A3BBarsMiMo-V2.5-ProTies
Coding03
Intelligence01
Agentic work01
Reasoning05
Math02
Knowledge04
Web design05
General021
All shared boards042
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
LMArena WebDevNot measured1480Only MiMo-V2.5-Pro measured
AA Coding IndexNot measured60.2Only MiMo-V2.5-Pro measured
LiveCodeBench (Vals AI)Not measured81.3%Only MiMo-V2.5-Pro measured
SWE-bench Verified (Vals AI)Not measured74.0%Only MiMo-V2.5-Pro measured
Terminal-Bench 4 (Vals AI)Not measured0.5%Only MiMo-V2.5-Pro measured
Vibe Code Bench (Vals AI)Not measured34.1%Only MiMo-V2.5-Pro measured
Code migration (Vals AI)Not measured21.6%Only MiMo-V2.5-Pro measured
Terminal-Bench 2.1 (Vals AI)Not measured57.3%Only MiMo-V2.5-Pro measured
LiveCodeBench (Artificial Analysis run)50.6%Not measuredOnly Qwen3 30B A3B measured
SciCodeNot measured50.6%Only MiMo-V2.5-Pro measured
Terminal-Bench Hard (Artificial Analysis run)6.8%43.2%MiMo-V2.5-Pro
WeirdML29.8%Not measuredOnly Qwen3 30B A3B measured
ALE-BenchNot measured899.8Only MiMo-V2.5-Pro measured
LMArena Text: coding13371501MiMo-V2.5-Pro
LMArena Text: software and IT13401495MiMo-V2.5-Pro
LMArena WebDev: ReactNot measured1469Only MiMo-V2.5-Pro measured
LMArena WebDev: HTMLNot measured1473Only MiMo-V2.5-Pro measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
AA Intelligence Index7.626.0MiMo-V2.5-Pro
Epoch Capabilities Index137.3Not measuredOnly Qwen3 30B A3B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
AA Agentic IndexNot measured21.3Only MiMo-V2.5-Pro measured
Finance Agent (Vals AI)Not measured41.5%Only MiMo-V2.5-Pro measured
Tax Agent Bench (Vals AI)Not measured11.5%Only MiMo-V2.5-Pro measured
Legal Research Bench (Vals AI)Not measured15.9%Only MiMo-V2.5-Pro measured
Excel Modeling Benchmark (Vals AI)Not measured55.2%Only MiMo-V2.5-Pro measured
τ²-Bench Telecom26.0%94.2%MiMo-V2.5-Pro
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
GPQA DiamondNot measured82.6%Only MiMo-V2.5-Pro measured
GPQA Diamond (Artificial Analysis run)61.6%86.6%MiMo-V2.5-Pro
Humanity's Last Exam (Artificial Analysis run)6.2%35.7%MiMo-V2.5-Pro
GPQA Diamond (Epoch AI run)61.7%Not measuredOnly Qwen3 30B A3B measured
LMArena Text: hard prompts13141486MiMo-V2.5-Pro
LMArena Text: expert13141501MiMo-V2.5-Pro
LMArena Text: hard prompts in English13291494MiMo-V2.5-Pro
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
AA Math Index72.3Not measuredOnly Qwen3 30B A3B measured
AIME 2025 (Artificial Analysis run)72.3%Not measuredOnly Qwen3 30B A3B measured
OTIS Mock AIME62.8%Not measuredOnly Qwen3 30B A3B measured
ProofBenchNot measured22.0%Only MiMo-V2.5-Pro measured
LMArena Text: math13551481MiMo-V2.5-Pro
LMArena Text: mathematical work13631491MiMo-V2.5-Pro
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 Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
MMLU ProNot measured84.6%Only MiMo-V2.5-Pro measured
LegalBench (Vals AI)Not measured77.1%Only MiMo-V2.5-Pro measured
CorpFin (Vals AI)Not measured61.4%Only MiMo-V2.5-Pro measured
TaxEval (Vals AI)Not measured73.8%Only MiMo-V2.5-Pro measured
MedCode (Vals AI)Not measured32.5%Only MiMo-V2.5-Pro measured
MMLU Pro (Artificial Analysis run)77.7%Not measuredOnly Qwen3 30B A3B measured
LMArena Text: science13211482MiMo-V2.5-Pro
LMArena Text: medicine and healthcare13181473MiMo-V2.5-Pro
LMArena Text: legal and government13141474MiMo-V2.5-Pro
LMArena Text: business and finance13091466MiMo-V2.5-Pro
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index05
Web design benchmarks for Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
Design Arena: websites9541266MiMo-V2.5-Pro
Design Arena: UI components9431246MiMo-V2.5-Pro
Design Arena: game dev8981261MiMo-V2.5-Pro
Design Arena: data viz9671257MiMo-V2.5-Pro
Design Arena: 3DNot measured1243Only MiMo-V2.5-Pro measured
Design Arena: all code categories9411265MiMo-V2.5-Pro
Design Arena: SVGNot measured1181Only MiMo-V2.5-Pro measured
Design Arena: ASCII artNot measured1156Only MiMo-V2.5-Pro measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index021
General benchmarks for Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
MedScribe (Vals AI)Not measured83.7%Only MiMo-V2.5-Pro measured
IFBench41.5%79.9%MiMo-V2.5-Pro
Long context reasoning (AA-LCR)0.0%79.7%MiMo-V2.5-Pro
DTBench60.3%84.5%MiMo-V2.5-Pro
LMCA15.8%29.5%MiMo-V2.5-Pro
Fiction.LiveBench40.6%Not measuredOnly Qwen3 30B A3B measured
Creative writing (Lech Mazur)75.3%Not measuredOnly Qwen3 30B A3B measured
LMArena Text13171464MiMo-V2.5-Pro
LMArena Text: instruction following12831475MiMo-V2.5-Pro
LMArena Text: creative writing12711438MiMo-V2.5-Pro
LMArena Text: English13351477MiMo-V2.5-Pro
LMArena Text: non-English12951448MiMo-V2.5-Pro
LMArena Text: Chinese13471507MiMo-V2.5-Pro
LMArena Text: German13071459MiMo-V2.5-Pro
LMArena Text: Japanese12541410MiMo-V2.5-Pro
LMArena Text: Korean12611435MiMo-V2.5-Pro
LMArena Text: French13521487MiMo-V2.5-Pro
LMArena Text: Spanish13171469MiMo-V2.5-Pro
LMArena Text: Russian12911449MiMo-V2.5-Pro
LMArena Text: Polish12991464MiMo-V2.5-Pro
LMArena Text: multi-turn13071476MiMo-V2.5-Pro
LMArena Text: longer queries13121481MiMo-V2.5-Pro
LMArena Text: writing and language12901451MiMo-V2.5-Pro
LMArena Text: entertainment and media12581438MiMo-V2.5-Pro
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 Qwen3 30B A3B and MiMo-V2.5-Pro
BenchmarkQwen3 30B A3BMiMo-V2.5-ProLeader
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

Qwen3 30B A3B$0.0004Fits in one request
MiMo-V2.5-Pro$0.0009Fits in one request

Qwen3 30B A3B costs less

Repository review

50K input + 3K output tokens

Qwen3 30B A3B$0.0075Exceeds the context window
MiMo-V2.5-Pro$0.026Fits in one request

Qwen3 30B A3B costs less

Agent loop

200K input + 10K output tokens

Qwen3 30B A3B$0.029Exceeds the context window
MiMo-V2.5-Pro$0.101Fits in one request

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 Qwen3 30B A3B and MiMo-V2.5-Pro
SpecificationQwen3 30B A3BXiaomi MiMo-V2.5-Pro
MakerQwenXiaomi
WeightsOpen weightsOpen weights
ReleasedApril 28, 2025April 22, 2026
Context window41K1.05M
Input $/Mtok$0.12$0.4575
Output $/Mtok$0.50$0.9152
Coding indexNot benchmarked31.6
Independent measurements behind it04
Cost per solved taskNot computable$0.03
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3 30B A3B better than MiMo-V2.5-Pro for coding?

Only MiMo-V2.5-Pro has a coding score, 31.6 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 1.8x cheaper ($0.50 vs $0.9152 per million).

Which is cheaper, Qwen3 30B A3B or MiMo-V2.5-Pro?

Qwen3 30B A3B costs $0.12 per million input tokens and $0.50 per million output tokens; MiMo-V2.5-Pro costs $0.4575 and $0.9152. Cost per solved task is known for MiMo-V2.5-Pro only.

Which has the bigger context window, Qwen3 30B A3B or MiMo-V2.5-Pro?

MiMo-V2.5-Pro, with 1.05M tokens against 41K.

How many benchmarks is the Qwen3 30B A3B vs MiMo-V2.5-Pro comparison based on?

42 benchmarks have a result for both models as of October 22, 2026. Qwen3 30B A3B's coding index rests on 0 independent benchmarks and MiMo-V2.5-Pro's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next