Claude Opus 5 vs Kimi K2.5

Claude Opus 5 leads Kimi K2.5 on coding, 83.0 to 38.6 on the Vibe Coding Index, and Kimi K2.5 costs 8.8x less per output token ($2.85 vs $25.00 per million). Updated October 22, 2026; 83 benchmarks have a result for both.

Replace Claude Opus 5 Replace Kimi K2.5

Claude Opus 5Anthropic

Coding: 83.0
Overall: 81.6
Output $/M: $25.00

Kimi K2.5Moonshot AI

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

vs boards won of 83 shared

Claude Opus 5 or Kimi K2.5: which to pick

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 38.6 for Kimi K2.5.

Pick Kimi K2.5 for output tokens 8.8x cheaper ($2.85 vs $25.00 per million) and a lower cost per solved task ($0.24 against $1.33).

Model AClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved task Model BKimi K2.5Moonshot AI38.6/1003 independent benchmarks$0.24 per solved task

834816

Shared results: 83
Claude Opus 5 only: 48
Kimi K2.5 only: 16
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
Claude Opus 5
Claude Opus 5 scores 83.0 against 38.6.
6 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Opus 5
Claude Opus 5 leads, 50.8 against 23.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Opus 5 has a AA Agentic Index result, 56.5.
Directional only
Reasoning
GPQA Diamond
Claude Opus 5
Claude Opus 5 leads, 93.4% 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
Claude Opus 5
Claude Opus 5 leads, 91.6% against 85.9%.
Same board, both measured
Web design
Design Arena: websites
Claude Opus 5
Claude Opus 5 leads, 1309 against 1248.
Same board, both measured
Long documents
Listed context window
Claude Opus 5
Claude Opus 5 takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2.5
Claude Opus 5 $0.018, Kimi K2.5 $0.0020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2.5
Claude Opus 5 $1.33, Kimi K2.5 $0.24.
Published attempt cost and pass rate

At a glance

Coding index: Claude Opus 5 83.0 from 6 benchmarks, Kimi K2.5 38.6 from 3 benchmarks.
Widest category: Coding, 32.6 points apart on average over 14 shared benchmarks.
Widest single gap: ARC-AGI-2: Claude Opus 5 90.4% against Kimi K2.5 11.8%, 78.6 points apart on a 0 to 100 scale.
Output price: Claude Opus 5 $25.00 against Kimi K2.5 $2.85 per million output tokens, 8.8x apart.
Context window: Claude Opus 5 takes 1M tokens, Kimi K2.5 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
Category	Claude Opus 5	Kimi K2.5
Coding	14	0
Intelligence	2	0
Agentic work	9	0
Reasoning	12	0
Math	2	0
Knowledge	10	0
Web design	8	0
General	25	1
All shared boards	82	1

CodingLike-for-likeSix of these boards feed the Vibe Coding Index140

Coding benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	Leader
SWE-bench Verified	Not measured	70.8%	Only Kimi K2.5 measured
SWE-bench Multilingual	Not measured	67.3%	Only Kimi K2.5 measured
LiveBench coding	90.8%	Not measured	Only Claude Opus 5 measured
LMArena WebDev	1689	1437	Claude Opus 5
AA Coding Index	78.0	46.8	Claude Opus 5
LiveCodeBench (Vals AI)	89.0%	83.9%	Claude Opus 5
SWE-bench Verified (Vals AI)	97.0%	70.0%	Claude Opus 5
Terminal-Bench 4 (Vals AI)	53.5%	Not measured	Only Claude Opus 5 measured
Vibe Code Bench (Vals AI)	88.4%	17.5%	Claude Opus 5
Code migration (Vals AI)	57.5%	7.0%	Claude Opus 5
ProgramBench (Vals AI)	3.0%	Not measured	Only Claude Opus 5 measured
IOI (Vals AI)	84.3%	Not measured	Only Claude Opus 5 measured
Terminal-Bench 2.1 (Vals AI)	84.6%	42.0%	Claude Opus 5
Vibe Code Bench 1-100 (Vals AI)	28.5%	Not measured	Only Claude Opus 5 measured
SkillsBench (Vals AI)	60.4%	Not measured	Only Claude Opus 5 measured
CyberBench (Vals AI)	65.4%	Not measured	Only Claude Opus 5 measured
SciCode	56.4%	Not measured	Only Claude Opus 5 measured
Terminal-Bench Hard (Artificial Analysis run)	Not measured	34.8%	Only Kimi K2.5 measured
Terminal-Bench	Not measured	43.2%	Only Kimi K2.5 measured
FrontierCode	53.4%	Not measured	Only Claude Opus 5 measured
FrontierSWE	52.0%	Not measured	Only Claude Opus 5 measured
WeirdML	91.8%	45.6%	Claude Opus 5
ALE-Bench	2164.6	821.6	Claude Opus 5
LMArena Text: coding	1533	1483	Claude Opus 5
LMArena Text: software and IT	1527	1471	Claude Opus 5
LMArena WebDev: React	1711	1429	Claude Opus 5
LMArena WebDev: HTML	1680	1426	Claude Opus 5
LMArena WebDev: from an image	1662	1439	Claude Opus 5
SciCode	13.8%	Not measured	Only Claude Opus 5 measured
Neither model has a result on the other 10 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20

Intelligence benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	Leader
AA Intelligence Index	50.8	23.5	Claude Opus 5
Epoch Capabilities Index	163.9	148.1	Claude Opus 5

Agentic workLike-for-likePublic boards, shown as published, kept out of the index90

Agentic work benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	Leader
AA Agentic Index	56.5	Not measured	Only Claude Opus 5 measured
Design Arena: agents building web apps	1266	1136	Claude Opus 5
Design Arena: agents building full-stack apps	1306	1114	Claude Opus 5
Design Arena: agents building mobile apps	1348	1147	Claude Opus 5
Design Arena: agents building Android apps	1257	1118	Claude Opus 5
Design Arena: agents building Godot games	1279	1219	Claude Opus 5
Design Arena: agents building games	1261	Not measured	Only Claude Opus 5 measured
Design Arena: PowerPoint slides	1240	Not measured	Only Claude Opus 5 measured
LiveBench research	88.9%	Not measured	Only Claude Opus 5 measured
LiveBench browser	84.0%	Not measured	Only Claude Opus 5 measured
LiveBench long agentic	62.1%	Not measured	Only Claude Opus 5 measured
SREBench (Vals AI)	12.2%	Not measured	Only Claude Opus 5 measured
Finance Agent (Vals AI)	58.6%	35.8%	Claude Opus 5
Tax Agent Bench (Vals AI)	45.5%	Not measured	Only Claude Opus 5 measured
Legal Research Bench (Vals AI)	55.3%	15.9%	Claude Opus 5
Excel Modeling Benchmark (Vals AI)	73.6%	28.5%	Claude Opus 5
BioMysteryBench (Vals AI)	79.3%	Not measured	Only Claude Opus 5 measured
Terminal-Bench-Science (Vals AI)	27.1%	Not measured	Only Claude Opus 5 measured
Vals Science Index	47.9%	Not measured	Only Claude Opus 5 measured
Time Horizon Index (Vals AI)	18.8%	Not measured	Only Claude Opus 5 measured
CUA-bench (Vals AI)	9.0%	Not measured	Only Claude Opus 5 measured
τ²-Bench Telecom	Not measured	95.9%	Only Kimi K2.5 measured
APEX-Agents	65.8%	Not measured	Only Claude Opus 5 measured
OSWorld 2.0	31.4%	Not measured	Only Claude Opus 5 measured
BALROG	63.4%	Not measured	Only Claude Opus 5 measured
PostTrainBench	35.0%	Not measured	Only Claude Opus 5 measured
OSWorld	Not measured	63.3%	Only Kimi K2.5 measured
Vending-Bench 2	$11,182	$1,198	Claude Opus 5
LMArena Search	1242	Not measured	Only Claude Opus 5 measured
Neither model has a result on the other 12 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index120

Reasoning benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	Leader
GPQA Diamond	93.4%	84.1%	Claude Opus 5
LiveBench reasoning	91.2%	Not measured	Only Claude Opus 5 measured
MysteryMechanism (Vals AI)	37.4%	Not measured	Only Claude Opus 5 measured
MMMU Pro (Vals AI)	89.9%	84.3%	Claude Opus 5
GPQA Diamond (Artificial Analysis run)	93.7%	87.9%	Claude Opus 5
Humanity's Last Exam (Artificial Analysis run)	54.9%	30.7%	Claude Opus 5
GPQA Diamond (Epoch AI run)	93.9%	Not measured	Only Claude Opus 5 measured
ARC-AGI	97.5%	65.3%	Claude Opus 5
ARC-AGI-2	90.4%	11.8%	Claude Opus 5
SimpleBench	80.6%	46.8%	Claude Opus 5
Chess puzzles	43.0%	Not measured	Only Claude Opus 5 measured
Mystery game puzzles	59.0%	Not measured	Only Claude Opus 5 measured
EBR-bench	45.7%	Not measured	Only Claude Opus 5 measured
LMArena Text: hard prompts	1527	1453	Claude Opus 5
LMArena Text: expert	1554	1466	Claude Opus 5
LMArena Text: hard prompts in English	1523	1460	Claude Opus 5
LMArena Vision: diagrams	1348	1282	Claude Opus 5
LMArena Vision: homework	1338	1297	Claude Opus 5
Kagi LLM Benchmark	Not measured	78.5%	Only Kimi K2.5 measured
Neither model has a result on the other 3 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index20

Math benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	Leader
AIME	Not measured	95.6%	Only Kimi K2.5 measured
OTIS Mock AIME	98.9%	Not measured	Only Claude Opus 5 measured
FrontierMath, tiers 1 to 3	85.6%	Not measured	Only Claude Opus 5 measured
FrontierMath, tier 4	73.2%	Not measured	Only Claude Opus 5 measured
ProofBench	99.0%	Not measured	Only Claude Opus 5 measured
LMArena Text: math	1533	1470	Claude Opus 5
LMArena Text: mathematical work	1544	1473	Claude Opus 5
Neither model has a result on the other 6 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100

Knowledge benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	Leader
MMLU Pro	91.6%	85.9%	Claude Opus 5
LegalBench (Vals AI)	87.0%	Not measured	Only Claude Opus 5 measured
CaseLaw (Vals AI)	Not measured	58.7%	Only Kimi K2.5 measured
CorpFin (Vals AI)	73.2%	68.3%	Claude Opus 5
TaxEval (Vals AI)	75.1%	74.2%	Claude Opus 5
MortgageTax (Vals AI)	72.1%	66.5%	Claude Opus 5
MedQA (Vals AI)	Not measured	94.4%	Only Kimi K2.5 measured
MedCode (Vals AI)	63.6%	39.3%	Claude Opus 5
SimpleQA Verified	59.9%	34.3%	Claude Opus 5
LMArena Text: science	1531	1459	Claude Opus 5
LMArena Text: medicine and healthcare	1525	1448	Claude Opus 5
LMArena Text: legal and government	1530	1441	Claude Opus 5
LMArena Text: business and finance	1501	1427	Claude Opus 5
Neither model has a result on the other 5 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index80

Web design benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	Leader
Design Arena: websites	1309	1248	Claude Opus 5
Design Arena: UI components	1346	1234	Claude Opus 5
Design Arena: game dev	1337	1206	Claude Opus 5
Design Arena: data viz	1329	1219	Claude Opus 5
Design Arena: 3D	1334	1204	Claude Opus 5
Design Arena: all code categories	1323	1236	Claude Opus 5
Design Arena: SVG	1311	1149	Claude Opus 5
Design Arena: ASCII art	1352	1166	Claude Opus 5
LiveBench design	83.0%	Not measured	Only Claude Opus 5 measured

GeneralLike-for-likePublic boards, shown as published, kept out of the index251

General benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	Leader
LiveBench data analysis	74.6%	Not measured	Only Claude Opus 5 measured
Public Benefits Bench (Vals AI)	76.9%	Not measured	Only Claude Opus 5 measured
SAGE (Vals AI)	49.4%	49.9%	Kimi K2.5
MedScribe (Vals AI)	91.0%	76.4%	Claude Opus 5
Vals Multimodal Index	73.9%	Not measured	Only Claude Opus 5 measured
IFBench	Not measured	70.2%	Only Kimi K2.5 measured
Long context reasoning (AA-LCR)	82.0%	78.0%	Claude Opus 5
DTBench	97.9%	Not measured	Only Claude Opus 5 measured
LMCA	64.5%	Not measured	Only Claude Opus 5 measured
Fiction.LiveBench	Not measured	86.1%	Only Kimi K2.5 measured
CL-bench	Not measured	19.3%	Only Kimi K2.5 measured
Furniture assembly	60.8%	Not measured	Only Claude Opus 5 measured
CL-bench Life	Not measured	13.2%	Only Kimi K2.5 measured
LMArena Text	1509	1445	Claude Opus 5
LMArena Text: instruction following	1518	1431	Claude Opus 5
LMArena Text: creative writing	1493	1422	Claude Opus 5
LMArena Vision	1320	1269	Claude Opus 5
LMArena Text: English	1508	1453	Claude Opus 5
LMArena Text: non-English	1502	1433	Claude Opus 5
LMArena Text: Chinese	1573	1494	Claude Opus 5
LMArena Text: German	1527	1441	Claude Opus 5
LMArena Text: Japanese	1520	1423	Claude Opus 5
LMArena Text: Korean	1517	1412	Claude Opus 5
LMArena Text: French	1519	1454	Claude Opus 5
LMArena Text: Spanish	1523	1450	Claude Opus 5
LMArena Text: Russian	1507	1435	Claude Opus 5
LMArena Text: Polish	1522	1445	Claude Opus 5
LMArena Text: multi-turn	1500	1444	Claude Opus 5
LMArena Text: longer queries	1517	1445	Claude Opus 5
LMArena Text: writing and language	1499	1425	Claude Opus 5
LMArena Text: entertainment and media	1481	1417	Claude Opus 5
LMArena Vision: English	1315	1274	Claude Opus 5
LMArena Vision: Chinese	1400	1328	Claude Opus 5
LMArena Vision: reading text	1329	1276	Claude Opus 5
LMArena Vision: humor	1293	1284	Claude Opus 5
LMArena Vision: captioning	Not measured	1257	Only Kimi K2.5 measured
LMArena Vision: recognizing things	Not measured	1285	Only Kimi K2.5 measured
LMArena Vision: creative writing	1313	1269	Claude Opus 5
LMArena Document	1516	Not measured	Only Claude Opus 5 measured
Neither model has a result on the other 7 boards here

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

Image generation benchmarks for Claude Opus 5 and Kimi K2.5
Benchmark	Claude Opus 5	Kimi K2.5	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

Claude Opus 5$0.018Fits in one request

Kimi K2.5$0.0020Fits in one request

Kimi K2.5 costs less

Repository review

50K input + 3K output tokens

Claude Opus 5$0.325Fits in one request

Kimi K2.5$0.035Fits in one request

Kimi K2.5 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 5$1.25Fits in one request

Kimi K2.5$0.135Fits 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 Claude Opus 5 and Kimi K2.5
Specification	Anthropic Claude Opus 5	MoonshotAI Kimi K2.5
Maker	Anthropic	Moonshot AI
Weights	No public weights listed	Open weights
Released	July 24, 2026	January 27, 2026
Context window	1M	262K
Input $/Mtok	$5.00	$0.532
Output $/Mtok	$25.00	$2.85
Coding index	83.0	38.6
Independent measurements behind it	6	3
Cost per solved task	$1.33	$0.24
Source	OpenRouter listing	OpenRouter listing

Questions

Is Claude Opus 5 better than Kimi K2.5 for coding?

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 38.6 for Kimi K2.5. Pick Kimi K2.5 for output tokens 8.8x cheaper ($2.85 vs $25.00 per million) and a lower cost per solved task ($0.24 against $1.33).

Which is cheaper, Claude Opus 5 or Kimi K2.5?

Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; Kimi K2.5 costs $0.532 and $2.85. Per solved SWE-bench Verified task, Claude Opus 5 costs $1.33 and Kimi K2.5 $0.24.

Which has the bigger context window, Claude Opus 5 or Kimi K2.5?

Claude Opus 5, with 1M tokens against 262K.

How many benchmarks is the Claude Opus 5 vs Kimi K2.5 comparison based on?

83 benchmarks have a result for both models as of October 22, 2026. Claude Opus 5's coding index rests on 6 independent benchmarks and Kimi K2.5'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/claude-opus-5-vs-kimi-k2-5" title="Claude Opus 5 vs Kimi K2.5, 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/claude-opus-5-vs-kimi-k2-5">LLMBenchmark.ai, Claude Opus 5 vs Kimi K2.5</a></p>

Claude Opus 5 or Kimi K2.5: 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