Enter opens the highlighted result. Esc closes.

Kimi K3 vs Qwen3 235B A22B Instruct 2507

Kimi K3 leads Qwen3 235B A22B Instruct 2507 on the Artificial Analysis Intelligence Index, 43.6 to 12.0, and Qwen3 235B A22B Instruct 2507 costs 19.4x less per output token ($0.775 vs $15.00 per million). Updated October 22, 2026; 16 benchmarks have a result for both.

Replace Kimi K3 Replace Qwen3 235B A22B Instruct 2507
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
16
Qwen3 235B A22B Instruct 2507Qwen
Coding
No data
Overall
No data
Output $/M
$0.775
0
vs boards won of 16 shared

Kimi K3 or Qwen3 235B A22B Instruct 2507: which to pick

Only Kimi K3 has a coding score, 62.3 on the Vibe Coding Index; Qwen3 235B A22B Instruct 2507 has none, so the two cannot be ranked on coding.

Pick Qwen3 235B A22B Instruct 2507 for output tokens 19.4x cheaper ($0.775 vs $15.00 per million).

Model AKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved taskModel BQwen3 235B A22B Instruct 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
16
Kimi K3 only
101
Qwen3 235B A22B Instruct 2507 only
8
Like-for-like categories
5 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 235B A22B Instruct 2507 not benchmarked.
Widest category
Reasoning, 47.0 points apart on average over 4 shared benchmarks.
Widest single gap
ARC-AGI: Kimi K3 94.5% against Qwen3 235B A22B Instruct 2507 11.0%, 83.5 points apart on a 0 to 100 scale.
Output price
Kimi K3 $15.00 against Qwen3 235B A22B Instruct 2507 $0.775 per million output tokens, 19.4x apart.
Context window
Kimi K3 takes 1.05M tokens, Qwen3 235B A22B Instruct 2507 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
CategoryKimi K3BarsQwen3 235B A22B Instruct 2507Ties
Coding20
Intelligence10
Reasoning40
Web design60
General30
All shared boards160
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for Kimi K3 and Qwen3 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
LiveBench coding59.3%Not measuredOnly Kimi K3 measured
LMArena WebDev1655Not measuredOnly Kimi K3 measured
AA Coding Index76.2Not measuredOnly Kimi K3 measured
LiveCodeBench (Vals AI)87.2%Not measuredOnly Kimi K3 measured
SWE-bench Verified (Vals AI)93.4%Not measuredOnly Kimi K3 measured
Terminal-Bench 4 (Vals AI)17.2%Not measuredOnly Kimi K3 measured
Vibe Code Bench (Vals AI)85.0%Not measuredOnly Kimi K3 measured
Code migration (Vals AI)16.1%Not measuredOnly Kimi K3 measured
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%Not measuredOnly Kimi K3 measured
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
LiveCodeBench (Artificial Analysis run)Not measured78.8%Only Qwen3 235B A22B Instruct 2507 measured
SciCode59.5%41.4%Kimi K3
Terminal-Bench Hard (Artificial Analysis run)Not measured15.2%Only Qwen3 235B A22B Instruct 2507 measured
FrontierCode44.2%Not measuredOnly Kimi K3 measured
FrontierSWE25.9%Not measuredOnly Kimi K3 measured
WeirdML82.6%38.7%Kimi K3
ALE-Bench1524.5Not measuredOnly Kimi K3 measured
LMArena Text: coding1508Not measuredOnly Kimi K3 measured
LMArena Text: software and IT1499Not measuredOnly Kimi K3 measured
LMArena WebDev: React1670Not measuredOnly Kimi K3 measured
LMArena WebDev: HTML1644Not measuredOnly Kimi K3 measured
LMArena WebDev: from an image1579Not measuredOnly Kimi K3 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Kimi K3 and Qwen3 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
AA Intelligence Index43.612.0Kimi K3
Epoch Capabilities Index157.9Not measuredOnly Kimi K3 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index26 boards, none shared
Agentic work benchmarks for Kimi K3 and Qwen3 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
AA Agentic Index50.0Not measuredOnly Kimi K3 measured
Design Arena: agents building web apps1295Not measuredOnly Kimi K3 measured
Design Arena: agents building full-stack apps1315Not measuredOnly Kimi K3 measured
Design Arena: agents building mobile apps1269Not measuredOnly Kimi K3 measured
Design Arena: agents building Android apps1253Not measuredOnly Kimi K3 measured
Design Arena: agents building Godot games1223Not measuredOnly Kimi K3 measured
Design Arena: agents building games1252Not measuredOnly Kimi K3 measured
Design Arena: HTML slides1206Not measuredOnly Kimi K3 measured
Design Arena: PowerPoint slides1248Not measuredOnly Kimi K3 measured
Design Arena: spreadsheets1096Not 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%Not measuredOnly Kimi K3 measured
Tax Agent Bench (Vals AI)33.4%Not measuredOnly Kimi K3 measured
Legal Research Bench (Vals AI)46.1%Not measuredOnly Kimi K3 measured
Harvey's Legal Agent Benchmark (Vals AI)12.9%Not measuredOnly Kimi K3 measured
Excel Modeling Benchmark (Vals AI)66.7%Not measuredOnly Kimi K3 measured
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 measured53.2%Only Qwen3 235B A22B Instruct 2507 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
Berkeley Function Calling Leaderboard (BFCL)Not measured52.1%Only Qwen3 235B A22B Instruct 2507 measured
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for Kimi K3 and Qwen3 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
GPQA Diamond92.9%Not measuredOnly Kimi K3 measured
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%79.0%Kimi K3
Humanity's Last Exam (Artificial Analysis run)46.9%15.9%Kimi K3
GPQA Diamond (Epoch AI run)93.1%Not measuredOnly Kimi K3 measured
ARC-AGI94.5%11.0%Kimi K3
ARC-AGI-260.4%1.3%Kimi K3
SimpleBench60.7%Not measuredOnly Kimi K3 measured
Chess puzzles37.0%Not measuredOnly Kimi K3 measured
Mystery game puzzles26.0%Not measuredOnly Kimi K3 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 8 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Math benchmarks for Kimi K3 and Qwen3 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
AA Math IndexNot measured91.0Only Qwen3 235B A22B Instruct 2507 measured
AIME 2025 (Artificial Analysis run)Not measured91.0%Only Qwen3 235B A22B Instruct 2507 measured
OTIS Mock AIME97.2%Not measuredOnly Kimi K3 measured
FrontierMath, tiers 1 to 372.2%Not measuredOnly Kimi K3 measured
FrontierMath, tier 439.0%Not measuredOnly Kimi K3 measured
ProofBench87.0%Not measuredOnly Kimi K3 measured
LMArena Text: math1494Not measuredOnly Kimi K3 measured
LMArena Text: mathematical work1505Not measuredOnly Kimi K3 measured
Neither model has a result on the other 5 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
Knowledge benchmarks for Kimi K3 and Qwen3 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
MMLU Pro88.0%Not measuredOnly Kimi K3 measured
LegalBench (Vals AI)86.2%Not measuredOnly Kimi K3 measured
CorpFin (Vals AI)71.6%Not measuredOnly Kimi K3 measured
TaxEval (Vals AI)75.7%Not measuredOnly Kimi K3 measured
MortgageTax (Vals AI)66.3%Not measuredOnly Kimi K3 measured
MedCode (Vals AI)49.4%Not measuredOnly Kimi K3 measured
MMLU Pro (Artificial Analysis run)Not measured84.3%Only Qwen3 235B A22B Instruct 2507 measured
SimpleQA Verified50.6%Not measuredOnly Kimi K3 measured
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 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Kimi K3 and Qwen3 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
Design Arena: websites13341058Kimi K3
Design Arena: UI components1340963Kimi K3
Design Arena: game dev1360951Kimi K3
Design Arena: data viz13521070Kimi K3
Design Arena: 3D1387994Kimi K3
Design Arena: all code categories13601038Kimi K3
Design Arena: SVG1302Not measuredOnly Kimi K3 measured
LiveBench design77.2%Not measuredOnly Kimi K3 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index30
General benchmarks for Kimi K3 and Qwen3 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
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%Not measuredOnly Kimi K3 measured
Vals Multimodal Index73.4%Not measuredOnly Kimi K3 measured
IFBenchNot measured51.2%Only Qwen3 235B A22B Instruct 2507 measured
Long context reasoning (AA-LCR)88.7%72.0%Kimi K3
DTBench91.2%78.4%Kimi K3
LMCA52.7%23.5%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 235B A22B Instruct 2507
BenchmarkKimi K3Qwen3 235B A22B Instruct 2507Leader
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 235B A22B Instruct 2507$0.0005Fits in one request

Qwen3 235B A22B Instruct 2507 costs less

Repository review

50K input + 3K output tokens

Kimi K3$0.195Fits in one request
Qwen3 235B A22B Instruct 2507$0.0096Fits in one request

Qwen3 235B A22B Instruct 2507 costs less

Agent loop

200K input + 10K output tokens

Kimi K3$0.750Fits in one request
Qwen3 235B A22B Instruct 2507$0.037Fits in one request

Qwen3 235B A22B Instruct 2507 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 235B A22B Instruct 2507
SpecificationMoonshotAI Kimi K3Qwen3 235B A22B Instruct 2507
MakerMoonshot AIQwen
WeightsOpen weightsOpen weights
ReleasedJuly 16, 2026July 21, 2025
Context window1.05M262K
Input $/Mtok$3.00$0.145
Output $/Mtok$15.00$0.775
Coding index62.3Not benchmarked
Independent measurements behind it60
Cost per solved task$0.81Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K3 better than Qwen3 235B A22B Instruct 2507 for coding?

Only Kimi K3 has a coding score, 62.3 on the Vibe Coding Index; Qwen3 235B A22B Instruct 2507 has none, so the two cannot be ranked on coding. Pick Qwen3 235B A22B Instruct 2507 for output tokens 19.4x cheaper ($0.775 vs $15.00 per million).

Which is cheaper, Kimi K3 or Qwen3 235B A22B Instruct 2507?

Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3 235B A22B Instruct 2507 costs $0.145 and $0.775. Cost per solved task is known for Kimi K3 only.

Which has the bigger context window, Kimi K3 or Qwen3 235B A22B Instruct 2507?

Kimi K3, with 1.05M tokens against 262K.

How many benchmarks is the Kimi K3 vs Qwen3 235B A22B Instruct 2507 comparison based on?

16 benchmarks have a result for both models as of October 22, 2026. Kimi K3's coding index rests on 6 independent benchmarks and Qwen3 235B A22B Instruct 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next