Enter opens the highlighted result. Esc closes.

Kimi K3 vs Qwen3.7 Max

Kimi K3 leads Qwen3.7 Max on coding, 62.3 to 54.1 on the Vibe Coding Index, and Qwen3.7 Max costs 3.4x less per output token ($4.425 vs $15.00 per million). Updated October 21, 2026; 54 benchmarks have a result for both.

Replace Kimi K3 Replace Qwen3.7 Max
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
49
Qwen3.7 MaxQwen
Coding
54.1
Overall
61.7
Output $/M
$4.425
5
vs boards won of 54 shared

Kimi K3 or Qwen3.7 Max: which to pick

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 54.1 for Qwen3.7 Max.

Pick Qwen3.7 Max for output tokens 3.4x cheaper ($4.425 vs $15.00 per million) and work measured by SimpleBench or Mystery game puzzles, where it leads.

Model AKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved taskModel BQwen3.7 MaxQwen54.1/1003 independent benchmarks$4.69 per solved task
Shared results
54
Kimi K3 only
63
Qwen3.7 Max only
5
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
Kimi K3 62.3 from 6 benchmarks, Qwen3.7 Max 54.1 from 3 benchmarks.
Widest category
Math, 18.8 points apart on average over 4 shared benchmarks.
Widest single gap
ProofBench: Kimi K3 87.0% against Qwen3.7 Max 26.0%, 61.0 points apart on a 0 to 100 scale.
Output price
Kimi K3 $15.00 against Qwen3.7 Max $4.425 per million output tokens, 3.4x apart.
Context window
Kimi K3 takes 1.05M tokens, Qwen3.7 Max 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
CategoryKimi K3BarsQwen3.7 MaxTies
Coding110
Intelligence20
Agentic work130
Reasoning52
Math40
Knowledge42
Web design70
General31
All shared boards495
CodingLike-for-likeSix of these boards feed the Vibe Coding Index110
Coding benchmarks for Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
LiveBench coding59.3%Not measuredOnly Kimi K3 measured
LMArena WebDev16551515Kimi K3
AA Coding Index76.266.0Kimi K3
LiveCodeBench (Vals AI)87.2%87.1%Kimi K3
SWE-bench Verified (Vals AI)93.4%68.8%Kimi K3
Terminal-Bench 4 (Vals AI)17.2%Not measuredOnly Kimi K3 measured
Vibe Code Bench (Vals AI)85.0%47.7%Kimi K3
Code migration (Vals AI)16.1%13.1%Kimi K3
ProgramBench (Vals AI)2.0%Not measuredOnly Kimi K3 measured
IOI (Vals AI)48.9%Not measuredOnly Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)80.9%61.0%Kimi K3
SWE-bench Multimodal (Vals AI)44.2%Not measuredOnly Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)18.2%Not measuredOnly Kimi K3 measured
CyberBench (Vals AI)75.2%Not measuredOnly Kimi K3 measured
SciCode59.5%49.5%Kimi K3
Terminal-Bench Hard (Artificial Analysis run)Not measured50.8%Only Qwen3.7 Max measured
FrontierCode44.2%Not measuredOnly Kimi K3 measured
FrontierSWE25.9%Not measuredOnly Kimi K3 measured
WeirdML82.6%Not measuredOnly Kimi K3 measured
ALE-Bench1524.51189.4Kimi K3
LMArena Text: coding1508Not measuredOnly Kimi K3 measured
LMArena Text: software and IT1499Not measuredOnly Kimi K3 measured
LMArena WebDev: React16701514Kimi K3
LMArena WebDev: HTML16441512Kimi K3
LMArena WebDev: from an image1579Not measuredOnly Kimi K3 measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
AA Intelligence Index43.629.5Kimi K3
Epoch Capabilities Index157.9154.0Kimi K3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index130
Agentic work benchmarks for Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
AA Agentic Index50.022.5Kimi K3
Design Arena: agents building web apps12951208Kimi K3
Design Arena: agents building full-stack apps13151191Kimi K3
Design Arena: agents building mobile apps12691155Kimi K3
Design Arena: agents building Android apps12501159Kimi K3
Design Arena: agents building Godot games12231187Kimi K3
Design Arena: agents building games12521161Kimi K3
Design Arena: HTML slides12561158Kimi K3
Design Arena: PowerPoint slides12731197Kimi K3
Design Arena: spreadsheets1058Not measuredOnly Kimi K3 measured
LiveBench research79.0%Not measuredOnly Kimi K3 measured
LiveBench browser16.0%Not measuredOnly Kimi K3 measured
LiveBench long agentic42.8%Not measuredOnly Kimi K3 measured
Finance Agent (Vals AI)53.1%47.8%Kimi K3
Tax Agent Bench (Vals AI)33.4%15.8%Kimi K3
Legal Research Bench (Vals AI)46.1%25.5%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)12.9%Not measuredOnly Kimi K3 measured
Excel Modeling Benchmark (Vals AI)66.7%57.0%Kimi K3
BioMysteryBench (Vals AI)72.6%Not measuredOnly Kimi K3 measured
Terminal-Bench-Science (Vals AI)1.4%Not measuredOnly Kimi K3 measured
Time Horizon Index (Vals AI)10.5%Not measuredOnly Kimi K3 measured
τ²-Bench TelecomNot measured94.7%Only Qwen3.7 Max measured
APEX-Agents47.8%Not measuredOnly Kimi K3 measured
PostTrainBench32.0%Not measuredOnly Kimi K3 measured
Vending-Bench 2$5,165Not measuredOnly Kimi K3 measured
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index52
Reasoning benchmarks for Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
GPQA Diamond92.9%90.2%Kimi K3
LiveBench reasoning90.7%Not measuredOnly Kimi K3 measured
MMMU Pro (Vals AI)88.2%Not measuredOnly Kimi K3 measured
GPQA Diamond (Artificial Analysis run)93.5%92.3%Kimi K3
Humanity's Last Exam (Artificial Analysis run)46.9%40.5%Kimi K3
GPQA Diamond (Epoch AI run)93.1%90.9%Kimi K3
ARC-AGI94.5%Not measuredOnly Kimi K3 measured
ARC-AGI-260.4%Not measuredOnly Kimi K3 measured
SimpleBench60.7%70.4%Qwen3.7 Max
Chess puzzles37.0%26.0%Kimi K3
Mystery game puzzles26.0%32.0%Qwen3.7 Max
EBR-benchNot measured9.5%Only Qwen3.7 Max measured
LMArena Text: hard prompts1495Not measuredOnly Kimi K3 measured
LMArena Text: expert1520Not measuredOnly Kimi K3 measured
LMArena Text: hard prompts in English1496Not measuredOnly Kimi K3 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
OTIS Mock AIME97.2%95.6%Kimi K3
FrontierMath, tiers 1 to 372.2%64.6%Kimi K3
FrontierMath, tier 439.0%34.1%Kimi K3
ProofBench87.0%26.0%Kimi K3
LMArena Text: math1494Not measuredOnly Kimi K3 measured
LMArena Text: mathematical work1505Not measuredOnly Kimi K3 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index42
Knowledge benchmarks for Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
MMLU Pro88.0%89.3%Qwen3.7 Max
LegalBench (Vals AI)86.2%84.9%Kimi K3
CorpFin (Vals AI)71.6%63.7%Kimi K3
TaxEval (Vals AI)75.7%75.3%Kimi K3
MortgageTax (Vals AI)66.3%Not measuredOnly Kimi K3 measured
MedCode (Vals AI)49.4%38.8%Kimi K3
SimpleQA Verified50.6%55.8%Qwen3.7 Max
LMArena Text: science1508Not measuredOnly Kimi K3 measured
LMArena Text: medicine and healthcare1489Not measuredOnly Kimi K3 measured
LMArena Text: legal and government1503Not measuredOnly Kimi K3 measured
LMArena Text: business and finance1470Not measuredOnly Kimi K3 measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index70
Web design benchmarks for Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
Design Arena: websites13351274Kimi K3
Design Arena: UI components13441270Kimi K3
Design Arena: game dev13591265Kimi K3
Design Arena: data viz13511275Kimi K3
Design Arena: 3D13881266Kimi K3
Design Arena: all code categories13601275Kimi K3
Design Arena: SVG13021217Kimi K3
Design Arena: ASCII artNot measured1211Only Qwen3.7 Max measured
LiveBench design77.2%Not measuredOnly Kimi K3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index31
General benchmarks for Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
Vals Index53.0%Not measuredOnly Kimi K3 measured
LiveBench data analysis78.7%Not measuredOnly Kimi K3 measured
Public Benefits Bench (Vals AI)68.2%Not measuredOnly Kimi K3 measured
SAGE (Vals AI)52.8%Not measuredOnly Kimi K3 measured
MedScribe (Vals AI)88.0%79.4%Kimi K3
Vals Multimodal Index73.4%Not measuredOnly Kimi K3 measured
IFBenchNot measured80.5%Only Qwen3.7 Max measured
Long context reasoning (AA-LCR)88.7%79.0%Kimi K3
DTBench91.2%92.3%Qwen3.7 Max
LMCA52.7%44.0%Kimi K3
Surface Evolver Bench95.0%Not measuredOnly Kimi K3 measured
Furniture assembly34.2%Not measuredOnly Kimi K3 measured
LMArena Text1476Not measuredOnly Kimi K3 measured
LMArena Text: instruction following1485Not measuredOnly Kimi K3 measured
LMArena Text: creative writing1457Not measuredOnly Kimi K3 measured
LMArena Text: English1481Not measuredOnly Kimi K3 measured
LMArena Text: non-English1466Not measuredOnly Kimi K3 measured
LMArena Text: Chinese1529Not measuredOnly Kimi K3 measured
LMArena Text: German1490Not measuredOnly Kimi K3 measured
LMArena Text: Japanese1494Not measuredOnly Kimi K3 measured
LMArena Text: Korean1460Not measuredOnly Kimi K3 measured
LMArena Text: French1492Not measuredOnly Kimi K3 measured
LMArena Text: Spanish1472Not measuredOnly Kimi K3 measured
LMArena Text: Russian1485Not measuredOnly Kimi K3 measured
LMArena Text: Polish1458Not measuredOnly Kimi K3 measured
LMArena Text: multi-turn1489Not measuredOnly Kimi K3 measured
LMArena Text: longer queries1494Not measuredOnly Kimi K3 measured
LMArena Text: writing and language1471Not measuredOnly Kimi K3 measured
LMArena Text: entertainment and media1453Not measuredOnly Kimi K3 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 Kimi K3 and Qwen3.7 Max
BenchmarkKimi K3Qwen3.7 MaxLeader
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

Kimi K3$0.011Fits in one request
Qwen3.7 Max$0.0037Fits in one request

Qwen3.7 Max costs less

Repository review

50K input + 3K output tokens

Kimi K3$0.195Fits in one request
Qwen3.7 Max$0.087Fits in one request

Qwen3.7 Max costs less

Agent loop

200K input + 10K output tokens

Kimi K3$0.750Fits in one request
Qwen3.7 Max$0.339Fits in one request

Qwen3.7 Max 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 Kimi K3 and Qwen3.7 Max
SpecificationMoonshotAI Kimi K3Qwen3.7 Max
MakerMoonshot AIQwen
WeightsOpen weightsNo public weights listed
ReleasedJuly 16, 2026May 21, 2026
Context window1.05M1M
Input $/Mtok$3.00$1.475
Output $/Mtok$15.00$4.425
Coding index62.354.1
Independent measurements behind it63
Cost per solved task$0.81$4.69
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K3 better than Qwen3.7 Max for coding?

Pick Kimi K3 for coding: it scores 62.3 on the Vibe Coding Index against 54.1 for Qwen3.7 Max. Pick Qwen3.7 Max for output tokens 3.4x cheaper ($4.425 vs $15.00 per million) and work measured by SimpleBench or Mystery game puzzles, where it leads.

Which is cheaper, Kimi K3 or Qwen3.7 Max?

Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.7 Max costs $1.475 and $4.425. Per solved SWE-bench Verified task, Kimi K3 costs $0.81 and Qwen3.7 Max $4.69.

Which has the bigger context window, Kimi K3 or Qwen3.7 Max?

Kimi K3, with 1.05M tokens against 1M.

How many benchmarks is the Kimi K3 vs Qwen3.7 Max comparison based on?

54 benchmarks have a result for both models as of October 21, 2026. Kimi K3's coding index rests on 6 independent benchmarks and Qwen3.7 Max'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/kimi-k3-vs-qwen3-7-max" title="Kimi K3 vs Qwen3.7 Max, 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/kimi-k3-vs-qwen3-7-max">LLMBenchmark.ai, Kimi K3 vs Qwen3.7 Max</a></p>