Kimi K2.5 vs Qwen3.8 Max (0902)

Qwen3.8 Max (0902) leads Kimi K2.5 on coding, 62.4 to 38.6 on the Vibe Coding Index, and Kimi K2.5 costs 2.1x less per output token ($2.85 vs $6.00 per million). Updated October 22, 2026; 76 benchmarks have a result for both.

Replace Kimi K2.5 Replace Qwen3.8 Max (0902)

Kimi K2.5Moonshot AI

Coding: 38.6
Overall: 44.8
Output $/M: $2.85

Qwen3.8 Max (0902)Qwen

Coding: 62.4
Overall: 68.9
Output $/M: $6.00

vs boards won of 76 shared

Kimi K2.5 or Qwen3.8 Max (0902): which to pick

Pick Qwen3.8 Max (0902) for coding: it scores 62.4 on the Vibe Coding Index against 38.6 for Kimi K2.5.

Pick Kimi K2.5 for output tokens 2.1x cheaper ($2.85 vs $6.00 per million) and a lower cost per solved task ($0.24 against $1.32).

Model AKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task Model BQwen3.8 Max (0902)Qwen62.4/1005 independent benchmarks$1.32 per solved task

762337

Shared results: 76
Kimi K2.5 only: 23
Qwen3.8 Max (0902) only: 37
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.

Coding
Vibe Coding Index, six public coding benchmarks
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) scores 62.4 against 38.6.
3 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 45.4 against 23.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3.8 Max (0902) has a AA Agentic Index result, 56.0.
Directional only
Reasoning
GPQA Diamond
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 93.7% against 84.1%.
Same board, both measured
Math
AIME
No call
Only Kimi K2.5 has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 88.6% against 85.9%.
Same board, both measured
Web design
Design Arena: websites
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 1275 against 1248.
Same board, both measured
Long documents
Listed context window
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2.5
Kimi K2.5 $0.0020, Qwen3.8 Max (0902) $0.0050 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2.5
Kimi K2.5 $0.24, Qwen3.8 Max (0902) $1.32.
Published attempt cost and pass rate

At a glance

Coding index: Kimi K2.5 38.6 from 3 benchmarks, Qwen3.8 Max (0902) 62.4 from 5 benchmarks.
Widest category: Coding, 22.0 points apart on average over 12 shared benchmarks.
Widest single gap: Vibe Code Bench (Vals AI): Kimi K2.5 17.5% against Qwen3.8 Max (0902) 64.7%, 47.2 points apart on a 0 to 100 scale.
Output price: Kimi K2.5 $2.85 against Qwen3.8 Max (0902) $6.00 per million output tokens, 2.1x apart.
Context window: Kimi K2.5 takes 262K tokens, Qwen3.8 Max (0902) 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
Category	Kimi K2.5	Qwen3.8 Max (0902)
Coding	0	12
Intelligence	0	2
Agentic work	0	8
Reasoning	0	9
Math	0	2
Knowledge	2	8
Web design	0	7
General	0	26
All shared boards	2	74

CodingLike-for-likeSix of these boards feed the Vibe Coding Index012

Coding benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
SWE-bench Verified	70.8%	Not measured	Only Kimi K2.5 measured
SWE-bench Multilingual	67.3%	Not measured	Only Kimi K2.5 measured
LiveBench coding	Not measured	60.3%	Only Qwen3.8 Max (0902) measured
LMArena WebDev	1437	1674	Qwen3.8 Max (0902)
AA Coding Index	46.8	76.2	Qwen3.8 Max (0902)
LiveCodeBench (Vals AI)	83.9%	87.8%	Qwen3.8 Max (0902)
SWE-bench Verified (Vals AI)	70.0%	85.6%	Qwen3.8 Max (0902)
Terminal-Bench 4 (Vals AI)	Not measured	34.3%	Only Qwen3.8 Max (0902) measured
Vibe Code Bench (Vals AI)	17.5%	64.7%	Qwen3.8 Max (0902)
Code migration (Vals AI)	7.0%	24.0%	Qwen3.8 Max (0902)
ProgramBench (Vals AI)	Not measured	0.0%	Only Qwen3.8 Max (0902) measured
IOI (Vals AI)	Not measured	68.9%	Only Qwen3.8 Max (0902) measured
Terminal-Bench 2.1 (Vals AI)	42.0%	67.4%	Qwen3.8 Max (0902)
SWE-bench Multimodal (Vals AI)	Not measured	42.5%	Only Qwen3.8 Max (0902) measured
Vibe Code Bench 1-100 (Vals AI)	Not measured	12.8%	Only Qwen3.8 Max (0902) measured
SkillsBench (Vals AI)	Not measured	42.0%	Only Qwen3.8 Max (0902) measured
CyberBench (Vals AI)	Not measured	28.6%	Only Qwen3.8 Max (0902) measured
SciCode	Not measured	53.2%	Only Qwen3.8 Max (0902) measured
Terminal-Bench Hard (Artificial Analysis run)	34.8%	Not measured	Only Kimi K2.5 measured
Terminal-Bench	43.2%	Not measured	Only Kimi K2.5 measured
FrontierSWE	Not measured	17.8%	Only Qwen3.8 Max (0902) measured
WeirdML	45.6%	Not measured	Only Kimi K2.5 measured
ALE-Bench	821.6	Not measured	Only Kimi K2.5 measured
LMArena Text: coding	1483	1502	Qwen3.8 Max (0902)
LMArena Text: software and IT	1471	1498	Qwen3.8 Max (0902)
LMArena WebDev: React	1429	1692	Qwen3.8 Max (0902)
LMArena WebDev: HTML	1426	1649	Qwen3.8 Max (0902)
LMArena WebDev: from an image	1439	1637	Qwen3.8 Max (0902)
Neither model has a result on the other 11 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02

Intelligence benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
AA Intelligence Index	23.5	45.4	Qwen3.8 Max (0902)
Epoch Capabilities Index	148.1	157.4	Qwen3.8 Max (0902)

Agentic workLike-for-likePublic boards, shown as published, kept out of the index08

Agentic work benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
AA Agentic Index	Not measured	56.0	Only Qwen3.8 Max (0902) measured
Design Arena: agents building web apps	1136	1300	Qwen3.8 Max (0902)
Design Arena: agents building full-stack apps	1114	1305	Qwen3.8 Max (0902)
Design Arena: agents building mobile apps	1147	1224	Qwen3.8 Max (0902)
Design Arena: agents building Android apps	1118	1196	Qwen3.8 Max (0902)
Design Arena: agents building Godot games	1219	1234	Qwen3.8 Max (0902)
Design Arena: PowerPoint slides	Not measured	1233	Only Qwen3.8 Max (0902) measured
Design Arena: spreadsheets	Not measured	967	Only Qwen3.8 Max (0902) measured
LiveBench research	Not measured	69.9%	Only Qwen3.8 Max (0902) measured
LiveBench browser	Not measured	32.0%	Only Qwen3.8 Max (0902) measured
LiveBench long agentic	Not measured	42.3%	Only Qwen3.8 Max (0902) measured
Finance Agent (Vals AI)	35.8%	50.6%	Qwen3.8 Max (0902)
Tax Agent Bench (Vals AI)	Not measured	32.1%	Only Qwen3.8 Max (0902) measured
Legal Research Bench (Vals AI)	15.9%	47.6%	Qwen3.8 Max (0902)
Excel Modeling Benchmark (Vals AI)	28.5%	60.1%	Qwen3.8 Max (0902)
Terminal-Bench-Science (Vals AI)	Not measured	12.9%	Only Qwen3.8 Max (0902) measured
τ²-Bench Telecom	95.9%	Not measured	Only Kimi K2.5 measured
APEX-Agents	Not measured	63.3%	Only Qwen3.8 Max (0902) measured
OSWorld	63.3%	Not measured	Only Kimi K2.5 measured
Vending-Bench 2	$1,198	Not measured	Only Kimi K2.5 measured
LMArena Search	Not measured	1261	Only Qwen3.8 Max (0902) measured
Neither model has a result on the other 20 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index09

Reasoning benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
GPQA Diamond	84.1%	93.7%	Qwen3.8 Max (0902)
LiveBench reasoning	Not measured	88.2%	Only Qwen3.8 Max (0902) measured
MysteryMechanism (Vals AI)	Not measured	23.9%	Only Qwen3.8 Max (0902) measured
MMMU Pro (Vals AI)	84.3%	88.0%	Qwen3.8 Max (0902)
GPQA Diamond (Artificial Analysis run)	87.9%	92.8%	Qwen3.8 Max (0902)
Humanity's Last Exam (Artificial Analysis run)	30.7%	43.1%	Qwen3.8 Max (0902)
GPQA Diamond (Epoch AI run)	Not measured	92.7%	Only Qwen3.8 Max (0902) measured
ARC-AGI	65.3%	Not measured	Only Kimi K2.5 measured
ARC-AGI-2	11.8%	Not measured	Only Kimi K2.5 measured
SimpleBench	46.8%	Not measured	Only Kimi K2.5 measured
Chess puzzles	Not measured	46.0%	Only Qwen3.8 Max (0902) measured
Mystery game puzzles	Not measured	38.0%	Only Qwen3.8 Max (0902) measured
LMArena Text: hard prompts	1453	1496	Qwen3.8 Max (0902)
LMArena Text: expert	1466	1507	Qwen3.8 Max (0902)
LMArena Text: hard prompts in English	1460	1503	Qwen3.8 Max (0902)
LMArena Vision: diagrams	1282	1323	Qwen3.8 Max (0902)
LMArena Vision: homework	1297	1336	Qwen3.8 Max (0902)
Kagi LLM Benchmark	78.5%	Not measured	Only Kimi K2.5 measured
Neither model has a result on the other 4 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index02

Math benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
AIME	95.6%	Not measured	Only Kimi K2.5 measured
OTIS Mock AIME	Not measured	100.0%	Only Qwen3.8 Max (0902) measured
FrontierMath, tiers 1 to 3	Not measured	74.7%	Only Qwen3.8 Max (0902) measured
FrontierMath, tier 4	Not measured	46.3%	Only Qwen3.8 Max (0902) measured
ProofBench	Not measured	58.0%	Only Qwen3.8 Max (0902) measured
LMArena Text: math	1470	1501	Qwen3.8 Max (0902)
LMArena Text: mathematical work	1473	1491	Qwen3.8 Max (0902)
Neither model has a result on the other 6 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index28

Knowledge benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
MMLU Pro	85.9%	88.6%	Qwen3.8 Max (0902)
LegalBench (Vals AI)	Not measured	83.6%	Only Qwen3.8 Max (0902) measured
CaseLaw (Vals AI)	58.7%	Not measured	Only Kimi K2.5 measured
CorpFin (Vals AI)	68.3%	65.8%	Kimi K2.5
TaxEval (Vals AI)	74.2%	75.5%	Qwen3.8 Max (0902)
MortgageTax (Vals AI)	66.5%	64.0%	Kimi K2.5
MedQA (Vals AI)	94.4%	Not measured	Only Kimi K2.5 measured
MedCode (Vals AI)	39.3%	40.7%	Qwen3.8 Max (0902)
SimpleQA Verified	34.3%	47.3%	Qwen3.8 Max (0902)
LMArena Text: science	1459	1512	Qwen3.8 Max (0902)
LMArena Text: medicine and healthcare	1448	1503	Qwen3.8 Max (0902)
LMArena Text: legal and government	1441	1492	Qwen3.8 Max (0902)
LMArena Text: business and finance	1427	1480	Qwen3.8 Max (0902)
Neither model has a result on the other 5 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index07

Web design benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
Design Arena: websites	1248	1275	Qwen3.8 Max (0902)
Design Arena: UI components	1234	1338	Qwen3.8 Max (0902)
Design Arena: game dev	1206	1312	Qwen3.8 Max (0902)
Design Arena: data viz	1219	1281	Qwen3.8 Max (0902)
Design Arena: 3D	1204	1336	Qwen3.8 Max (0902)
Design Arena: all code categories	1236	1293	Qwen3.8 Max (0902)
Design Arena: SVG	1149	Not measured	Only Kimi K2.5 measured
Design Arena: ASCII art	1166	1200	Qwen3.8 Max (0902)
LiveBench design	Not measured	78.6%	Only Qwen3.8 Max (0902) measured

GeneralLike-for-likePublic boards, shown as published, kept out of the index026

General benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
LiveBench data analysis	Not measured	78.4%	Only Qwen3.8 Max (0902) measured
Public Benefits Bench (Vals AI)	Not measured	67.1%	Only Qwen3.8 Max (0902) measured
SAGE (Vals AI)	49.9%	51.2%	Qwen3.8 Max (0902)
MedScribe (Vals AI)	76.4%	85.0%	Qwen3.8 Max (0902)
Vals Multimodal Index	Not measured	65.4%	Only Qwen3.8 Max (0902) measured
IFBench	70.2%	Not measured	Only Kimi K2.5 measured
Long context reasoning (AA-LCR)	78.0%	80.3%	Qwen3.8 Max (0902)
DTBench	Not measured	92.0%	Only Qwen3.8 Max (0902) measured
LMCA	Not measured	46.2%	Only Qwen3.8 Max (0902) measured
Fiction.LiveBench	86.1%	Not measured	Only Kimi K2.5 measured
CL-bench	19.3%	Not measured	Only Kimi K2.5 measured
Furniture assembly	Not measured	20.0%	Only Qwen3.8 Max (0902) measured
CL-bench Life	13.2%	Not measured	Only Kimi K2.5 measured
LMArena Text	1445	1483	Qwen3.8 Max (0902)
LMArena Text: instruction following	1431	1481	Qwen3.8 Max (0902)
LMArena Text: creative writing	1422	1477	Qwen3.8 Max (0902)
LMArena Vision	1269	1313	Qwen3.8 Max (0902)
LMArena Text: English	1453	1491	Qwen3.8 Max (0902)
LMArena Text: non-English	1433	1473	Qwen3.8 Max (0902)
LMArena Text: Chinese	1494	1539	Qwen3.8 Max (0902)
LMArena Text: German	1441	1478	Qwen3.8 Max (0902)
LMArena Text: Japanese	1423	1473	Qwen3.8 Max (0902)
LMArena Text: Korean	1412	1460	Qwen3.8 Max (0902)
LMArena Text: French	1454	1498	Qwen3.8 Max (0902)
LMArena Text: Spanish	1450	1489	Qwen3.8 Max (0902)
LMArena Text: Russian	1435	1482	Qwen3.8 Max (0902)
LMArena Text: Polish	1445	1471	Qwen3.8 Max (0902)
LMArena Text: multi-turn	1444	1489	Qwen3.8 Max (0902)
LMArena Text: longer queries	1445	1488	Qwen3.8 Max (0902)
LMArena Text: writing and language	1425	1477	Qwen3.8 Max (0902)
LMArena Text: entertainment and media	1417	1464	Qwen3.8 Max (0902)
LMArena Vision: English	1274	1311	Qwen3.8 Max (0902)
LMArena Vision: Chinese	1328	1358	Qwen3.8 Max (0902)
LMArena Vision: reading text	1276	1322	Qwen3.8 Max (0902)
LMArena Vision: humor	1284	1304	Qwen3.8 Max (0902)
LMArena Vision: captioning	1257	Not measured	Only Kimi K2.5 measured
LMArena Vision: recognizing things	1285	Not measured	Only Kimi K2.5 measured
LMArena Vision: creative writing	1269	1312	Qwen3.8 Max (0902)
Neither model has a result on the other 8 boards here

Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared

Image generation benchmarks for Kimi K2.5 and Qwen3.8 Max (0902)
Benchmark	Kimi K2.5	Qwen3.8 Max (0902)	Leader
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 K2.5$0.0020Fits in one request

Qwen3.8 Max (0902)$0.0050Fits in one request

Kimi K2.5 costs less

Repository review

50K input + 3K output tokens

Kimi K2.5$0.035Fits in one request

Qwen3.8 Max (0902)$0.118Fits in one request

Kimi K2.5 costs less

Agent loop

200K input + 10K output tokens

Kimi K2.5$0.135Fits in one request

Qwen3.8 Max (0902)$0.460Fits in one request

Kimi K2.5 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 K2.5 and Qwen3.8 Max (0902)
Specification	MoonshotAI Kimi K2.5	Qwen3.8 Max (0902)
Maker	Moonshot AI	Qwen
Weights	Open weights	No public weights listed
Released	January 27, 2026	September 3, 2026
Context window	262K	1M
Input $/Mtok	$0.532	$2.00
Output $/Mtok	$2.85	$6.00
Coding index	38.6	62.4
Independent measurements behind it	3	5
Cost per solved task	$0.24	$1.32
Source	OpenRouter listing	OpenRouter listing

Questions

Is Kimi K2.5 better than Qwen3.8 Max (0902) for coding?

Pick Qwen3.8 Max (0902) for coding: it scores 62.4 on the Vibe Coding Index against 38.6 for Kimi K2.5. Pick Kimi K2.5 for output tokens 2.1x cheaper ($2.85 vs $6.00 per million) and a lower cost per solved task ($0.24 against $1.32).

Which is cheaper, Kimi K2.5 or Qwen3.8 Max (0902)?

Kimi K2.5 costs $0.532 per million input tokens and $2.85 per million output tokens; Qwen3.8 Max (0902) costs $2.00 and $6.00. Per solved SWE-bench Verified task, Kimi K2.5 costs $0.24 and Qwen3.8 Max (0902) $1.32.

Which has the bigger context window, Kimi K2.5 or Qwen3.8 Max (0902)?

Qwen3.8 Max (0902), with 1M tokens against 262K.

How many benchmarks is the Kimi K2.5 vs Qwen3.8 Max (0902) comparison based on?

76 benchmarks have a result for both models as of October 22, 2026. Kimi K2.5's coding index rests on 3 independent benchmarks and Qwen3.8 Max (0902)'s on 5. 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-k2-5-vs-qwen3-8-max-0902" title="Kimi K2.5 vs Qwen3.8 Max (0902), 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-k2-5-vs-qwen3-8-max-0902">LLMBenchmark.ai, Kimi K2.5 vs Qwen3.8 Max (0902)</a></p>

Kimi K2.5 or Qwen3.8 Max (0902): which to pick

Which one for your work

Coding

Intelligence

Agentic work

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next