Enter opens the highlighted result. Esc closes.

MiniMax M3 vs Qwen3 Coder 480B A35B

Updated October 21, 2026. 44 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace MiniMax M3 Replace Qwen3 Coder 480B A35B
MiniMax M3MiniMax
Coding
57.8
Overall
29.2
Output $/M
$1.20
44
Qwen3 Coder 480B A35BQwen
Coding
50.0
Overall
11.9
Output $/M
$1.00
0
vs boards won of 44 shared

Decision reading

Pick MiniMax M3 for coding: it scores 57.8 on the Vibe Coding Index against 50.0 for Qwen3 Coder 480B A35B.

Pick Qwen3 Coder 480B A35B when output tokens cost 1.2x less.

Model AMiniMax M3MiniMax57.8/1002 independent benchmarks$0.56 per solved taskModel BQwen3 Coder 480B A35BQwen50.0/1002 independent benchmarksNo cost per solved task
Shared results
44
MiniMax M3 only
72
Qwen3 Coder 480B A35B only
8
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 M3 57.8 from 2 benchmarks, Qwen3 Coder 480B A35B 50.0 from 2 benchmarks.
Widest category
Agentic work, 45.3 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: MiniMax M3 88.9% against Qwen3 Coder 480B A35B 43.6%, 45.3 points apart on a 0 to 100 scale.
Output price
MiniMax M3 $1.20 against Qwen3 Coder 480B A35B $1.00 per million output tokens, 1.2x apart.
Context window
MiniMax M3 takes 1.05M tokens, Qwen3 Coder 480B A35B 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 M3BarsQwen3 Coder 480B A35BTies
Coding70
Intelligence10
Agentic work10
Reasoning50
Math20
Knowledge40
Web design50
General190
All shared boards440
CodingLike-for-likeFour of these boards feed the Vibe Coding Index70
Coding benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
SWE-bench VerifiedNot measured69.6%Only Qwen3 Coder 480B A35B measured
LiveBench coding70.9%Not measuredOnly MiniMax M3 measured
LMArena WebDev14821275MiniMax M3
AA Coding Index58.6Not measuredOnly MiniMax M3 measured
LiveCodeBench (Vals AI)82.2%Not measuredOnly MiniMax M3 measured
SWE-bench Verified (Vals AI)75.0%Not measuredOnly MiniMax M3 measured
Terminal-Bench 4 (Vals AI)1.0%Not measuredOnly MiniMax M3 measured
Vibe Code Bench (Vals AI)47.6%Not measuredOnly MiniMax M3 measured
Code migration (Vals AI)19.9%Not measuredOnly MiniMax M3 measured
Terminal-Bench 2.1 (Vals AI)53.6%Not measuredOnly MiniMax M3 measured
SWE-bench Multimodal (Vals AI)33.3%Not measuredOnly MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)9.2%Not measuredOnly MiniMax M3 measured
SkillsBench (Vals AI)51.5%Not measuredOnly MiniMax M3 measured
CyberBench (Vals AI)65.0%Not measuredOnly MiniMax M3 measured
LiveCodeBench (Artificial Analysis run)Not measured58.5%Only Qwen3 Coder 480B A35B measured
SciCode47.1%Not measuredOnly MiniMax M3 measured
Terminal-Bench Hard (Artificial Analysis run)42.4%18.9%MiniMax M3
Terminal-BenchNot measured27.2%Only Qwen3 Coder 480B A35B measured
FrontierCode14.7%Not measuredOnly MiniMax M3 measured
GSO-BenchNot measured4.9%Only Qwen3 Coder 480B A35B measured
WeirdMLNot measured41.2%Only Qwen3 Coder 480B A35B measured
ALE-Bench640.0461.4MiniMax M3
LMArena Text: coding14701412MiniMax M3
LMArena Text: software and IT14661393MiniMax M3
LMArena WebDev: React14781257MiniMax M3
LMArena WebDev: HTML14551287MiniMax M3
LMArena WebDev: from an image1470Not measuredOnly MiniMax M3 measured
Neither model has a result on the other 11 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
AA Intelligence Index29.211.9MiniMax M3
Epoch Capabilities Index146.9Not measuredOnly MiniMax M3 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
AA Agentic Index29.5Not measuredOnly MiniMax M3 measured
Design Arena: agents building web apps1200Not measuredOnly MiniMax M3 measured
Design Arena: agents building full-stack apps1197Not measuredOnly MiniMax M3 measured
Design Arena: agents building mobile apps1169Not measuredOnly MiniMax M3 measured
Design Arena: agents building Android apps1164Not measuredOnly MiniMax M3 measured
Design Arena: agents building games1158Not measuredOnly MiniMax M3 measured
Design Arena: HTML slides1180Not measuredOnly MiniMax M3 measured
Design Arena: PowerPoint slides1205Not measuredOnly MiniMax M3 measured
Design Arena: spreadsheets1021Not measuredOnly MiniMax M3 measured
LiveBench research68.0%Not measuredOnly MiniMax M3 measured
LiveBench browser8.0%Not measuredOnly MiniMax M3 measured
LiveBench long agentic12.4%Not measuredOnly MiniMax M3 measured
Finance Agent (Vals AI)48.3%Not measuredOnly MiniMax M3 measured
Tax Agent Bench (Vals AI)20.6%Not measuredOnly MiniMax M3 measured
Legal Research Bench (Vals AI)29.8%Not measuredOnly MiniMax M3 measured
Excel Modeling Benchmark (Vals AI)47.8%Not measuredOnly MiniMax M3 measured
τ²-Bench Telecom88.9%43.6%MiniMax M3
APEX-Agents37.7%Not measuredOnly MiniMax M3 measured
OSWorld 2.04.6%Not measuredOnly MiniMax M3 measured
Vending-Bench 2$2,158Not measuredOnly MiniMax M3 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
GPQA Diamond92.7%Not measuredOnly MiniMax M3 measured
LiveBench reasoning74.5%Not measuredOnly MiniMax M3 measured
MMMU Pro (Vals AI)81.2%Not measuredOnly MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)92.9%61.8%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)39.0%4.5%MiniMax M3
GPQA Diamond (Epoch AI run)90.9%Not measuredOnly MiniMax M3 measured
SimpleBench45.8%Not measuredOnly MiniMax M3 measured
Chess puzzles13.0%Not measuredOnly MiniMax M3 measured
Mystery game puzzles8.0%Not measuredOnly MiniMax M3 measured
LMArena Text: hard prompts14471372MiniMax M3
LMArena Text: expert14611338MiniMax M3
LMArena Text: hard prompts in English14551380MiniMax M3
LMArena Vision: diagrams1266Not measuredOnly MiniMax M3 measured
LMArena Vision: homework1268Not measuredOnly MiniMax M3 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
AA Math IndexNot measured39.3Only Qwen3 Coder 480B A35B measured
AIME 2025 (Artificial Analysis run)Not measured39.3%Only Qwen3 Coder 480B A35B measured
OTIS Mock AIME71.1%Not measuredOnly MiniMax M3 measured
ProofBench18.0%Not measuredOnly MiniMax M3 measured
LMArena Text: math14291365MiniMax M3
LMArena Text: mathematical work14481367MiniMax M3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
MMLU Pro84.2%Not measuredOnly MiniMax M3 measured
LegalBench (Vals AI)85.4%Not measuredOnly MiniMax M3 measured
CorpFin (Vals AI)68.1%Not measuredOnly MiniMax M3 measured
TaxEval (Vals AI)72.7%Not measuredOnly MiniMax M3 measured
MortgageTax (Vals AI)68.4%Not measuredOnly MiniMax M3 measured
MedCode (Vals AI)46.3%Not measuredOnly MiniMax M3 measured
MMLU Pro (Artificial Analysis run)Not measured78.8%Only Qwen3 Coder 480B A35B measured
LMArena Text: science14521347MiniMax M3
LMArena Text: medicine and healthcare14411347MiniMax M3
LMArena Text: legal and government14371358MiniMax M3
LMArena Text: business and finance14341343MiniMax M3
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index50
Web design benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
Design Arena: websites12571159MiniMax M3
Design Arena: UI components12461112MiniMax M3
Design Arena: game dev12101099MiniMax M3
Design Arena: data viz12351084MiniMax M3
Design Arena: 3D1209Not measuredOnly MiniMax M3 measured
Design Arena: all code categories12471143MiniMax M3
Design Arena: SVG1161Not measuredOnly MiniMax M3 measured
Design Arena: ASCII art1161Not measuredOnly MiniMax M3 measured
LiveBench design66.2%Not measuredOnly MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
LiveBench data analysis76.2%Not measuredOnly MiniMax M3 measured
Public Benefits Bench (Vals AI)64.1%Not measuredOnly MiniMax M3 measured
SAGE (Vals AI)50.6%Not measuredOnly MiniMax M3 measured
MedScribe (Vals AI)87.3%Not measuredOnly MiniMax M3 measured
Vals Multimodal Index60.0%Not measuredOnly MiniMax M3 measured
IFBench82.9%40.5%MiniMax M3
Long context reasoning (AA-LCR)83.0%45.7%MiniMax M3
DTBench78.9%Not measuredOnly MiniMax M3 measured
LMCA33.7%Not measuredOnly MiniMax M3 measured
Surface Evolver Bench55.0%Not measuredOnly MiniMax M3 measured
LMArena Text14331357MiniMax M3
LMArena Text: instruction following14331355MiniMax M3
LMArena Text: creative writing14041333MiniMax M3
LMArena Vision1251Not measuredOnly MiniMax M3 measured
LMArena Text: English14431359MiniMax M3
LMArena Text: non-English14201346MiniMax M3
LMArena Text: Chinese14661357MiniMax M3
LMArena Text: German14281325MiniMax M3
LMArena Text: Japanese13801311MiniMax M3
LMArena Text: Korean13731305MiniMax M3
LMArena Text: French14441398MiniMax M3
LMArena Text: Spanish14331360MiniMax M3
LMArena Text: Russian14261366MiniMax M3
LMArena Text: Polish14231344MiniMax M3
LMArena Text: multi-turn14431366MiniMax M3
LMArena Text: longer queries14461378MiniMax M3
LMArena Text: writing and language14191340MiniMax M3
LMArena Text: entertainment and media14031317MiniMax M3
LMArena Vision: English1263Not measuredOnly MiniMax M3 measured
LMArena Vision: Chinese1311Not measuredOnly MiniMax M3 measured
LMArena Vision: reading text1259Not measuredOnly MiniMax M3 measured
LMArena Vision: humor1235Not measuredOnly MiniMax M3 measured
LMArena Vision: recognizing things1197Not measuredOnly MiniMax M3 measured
LMArena Vision: creative writing1234Not measuredOnly MiniMax M3 measured
LMArena Document1435Not measuredOnly MiniMax M3 measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M3 and Qwen3 Coder 480B A35B
BenchmarkMiniMax M3Qwen3 Coder 480B A35BLeader
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 M3$0.0009Fits in one request
Qwen3 Coder 480B A35B$0.0008Fits in one request

Qwen3 Coder 480B A35B costs less

Repository review

50K input + 3K output tokens

MiniMax M3$0.019Fits in one request
Qwen3 Coder 480B A35B$0.018Fits in one request

Qwen3 Coder 480B A35B costs less

Agent loop

200K input + 10K output tokens

MiniMax M3$0.072Fits in one request
Qwen3 Coder 480B A35B$0.070Fits in one request

Qwen3 Coder 480B A35B 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 M3 and Qwen3 Coder 480B A35B
SpecificationMiniMax M3Qwen3 Coder 480B A35B
MakerMiniMaxQwen
WeightsOpen weightsOpen weights
ReleasedMay 31, 2026July 23, 2025
Context window1.05M262K
Input $/Mtok$0.30$0.30
Output $/Mtok$1.20$1.00
Coding index57.850.0
Independent measurements behind it22
Cost per solved task$0.56Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M3 better than Qwen3 Coder 480B A35B for coding?

Pick MiniMax M3 for coding: it scores 57.8 on the Vibe Coding Index against 50.0 for Qwen3 Coder 480B A35B. Pick Qwen3 Coder 480B A35B when output tokens cost 1.2x less.

Which is cheaper, MiniMax M3 or Qwen3 Coder 480B A35B?

MiniMax M3 costs $0.30 per million input tokens and $1.20 per million output tokens; Qwen3 Coder 480B A35B costs $0.30 and $1.00. Cost per solved task is known for MiniMax M3 only.

Which has the bigger context window, MiniMax M3 or Qwen3 Coder 480B A35B?

MiniMax M3, with 1.05M tokens against 262K.

How many benchmarks is the MiniMax M3 vs Qwen3 Coder 480B A35B comparison based on?

44 benchmarks have a result for both models as of October 21, 2026. MiniMax M3's coding index rests on 2 independent benchmarks and Qwen3 Coder 480B A35B's on 2. 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-m3-vs-qwen3-coder" title="MiniMax M3 vs Qwen3 Coder 480B A35B, 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-m3-vs-qwen3-coder">LLMBenchmark.ai, MiniMax M3 vs Qwen3 Coder 480B A35B</a></p>