LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Kimi K2.5 vs Llama 4 Maverick

Updated October 21, 2026. 70 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Kimi K2.5 Replace Llama 4 Maverick
Kimi K2.5Moonshot AI
Coding
58.5
Overall
23.5
Output $/M
$2.50
70
Llama 4 MaverickMeta Llama
Coding
18.1
Overall
9.3
Output $/M
$0.6525
0
vs boards won of 70 shared

Decision reading

Pick Kimi K2.5 for coding: it scores 58.5 on the Vibe Coding Index against 18.1 for Llama 4 Maverick.

Pick Llama 4 Maverick when output tokens cost 3.8x less, or when the context window is larger, 524K against 262K tokens.

Model AKimi K2.5Moonshot AI58.5/1002 independent benchmarks$0.24 per solved taskModel BLlama 4 MaverickMeta Llama18.1/1002 independent benchmarks$1.491 per solved task
Shared results
70
Kimi K2.5 only
28
Llama 4 Maverick only
14
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
Kimi K2.5 58.5 from 2 benchmarks, Llama 4 Maverick 18.1 from 2 benchmarks.
Widest category
Agentic work, 78.1 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Kimi K2.5 95.9% against Llama 4 Maverick 17.8%, 78.1 points apart on a 0 to 100 scale.
Output price
Kimi K2.5 $2.50 against Llama 4 Maverick $0.6525 per million output tokens, 3.8x apart.
Context window
Kimi K2.5 takes 262K tokens, Llama 4 Maverick 524K.

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 K2.5BarsLlama 4 MaverickTies
Coding80
Intelligence20
Agentic work10
Reasoning120
Math30
Knowledge100
Web design60
General280
All shared boards700
CodingLike-for-likeFour of these boards feed the Vibe Coding Index80
Coding benchmarks for Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
Aider polyglotNot measured15.6%Only Llama 4 Maverick measured
SWE-bench Verified70.8%21.0%Kimi K2.5
SWE-bench Multilingual67.3%Not measuredOnly Kimi K2.5 measured
LMArena WebDev1437Not measuredOnly Kimi K2.5 measured
AA Coding Index46.816.3Kimi K2.5
LiveCodeBench (Vals AI)83.9%47.3%Kimi K2.5
SWE-bench Verified (Vals AI)70.0%Not measuredOnly Kimi K2.5 measured
Vibe Code Bench (Vals AI)17.5%Not measuredOnly Kimi K2.5 measured
Code migration (Vals AI)7.0%Not measuredOnly Kimi K2.5 measured
Terminal-Bench 2.1 (Vals AI)42.0%Not measuredOnly Kimi K2.5 measured
LiveCodeBench (Artificial Analysis run)Not measured39.7%Only Llama 4 Maverick measured
SciCodeNot measured31.7%Only Llama 4 Maverick measured
Terminal-Bench Hard (Artificial Analysis run)34.8%6.8%Kimi K2.5
Terminal-Bench43.2%Not measuredOnly Kimi K2.5 measured
WeirdML45.6%24.5%Kimi K2.5
ALE-Bench821.6173.0Kimi K2.5
LMArena Text: coding14831301Kimi K2.5
LMArena Text: software and IT14711299Kimi K2.5
LMArena WebDev: React1429Not measuredOnly Kimi K2.5 measured
LMArena WebDev: HTML1426Not measuredOnly Kimi K2.5 measured
LMArena WebDev: from an image1439Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
AA Intelligence Index23.59.3Kimi K2.5
Epoch Capabilities Index148.1132.2Kimi K2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
AA Agentic IndexNot measured0.6Only Llama 4 Maverick measured
Design Arena: agents building web apps1136Not measuredOnly Kimi K2.5 measured
Design Arena: agents building full-stack apps1114Not measuredOnly Kimi K2.5 measured
Design Arena: agents building mobile apps1147Not measuredOnly Kimi K2.5 measured
Design Arena: agents building Android apps1124Not measuredOnly Kimi K2.5 measured
Design Arena: agents building Godot games1219Not measuredOnly Kimi K2.5 measured
Finance Agent (Vals AI)35.8%Not measuredOnly Kimi K2.5 measured
Legal Research Bench (Vals AI)15.9%Not measuredOnly Kimi K2.5 measured
Excel Modeling Benchmark (Vals AI)28.5%Not measuredOnly Kimi K2.5 measured
τ²-Bench Telecom95.9%17.8%Kimi K2.5
OSWorld63.3%Not measuredOnly Kimi K2.5 measured
Vending-Bench 2$1,198Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
Reasoning benchmarks for Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
GPQA Diamond84.1%69.4%Kimi K2.5
MMMU Pro (Vals AI)84.3%71.7%Kimi K2.5
GPQA Diamond (Artificial Analysis run)87.9%67.1%Kimi K2.5
Humanity's Last Exam (Artificial Analysis run)30.7%4.9%Kimi K2.5
ARC-AGI65.3%4.4%Kimi K2.5
ARC-AGI-211.8%0.0%Kimi K2.5
SimpleBench46.8%27.7%Kimi K2.5
LMArena Text: hard prompts14531281Kimi K2.5
LMArena Text: expert14661259Kimi K2.5
LMArena Text: hard prompts in English14601295Kimi K2.5
LMArena Vision: diagrams12821134Kimi K2.5
LMArena Vision: homework12971164Kimi K2.5
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
AIME95.6%25.2%Kimi K2.5
MATH 500 (Vals AI)Not measured85.2%Only Llama 4 Maverick measured
MGSM (Vals AI)Not measured92.4%Only Llama 4 Maverick measured
AA Math IndexNot measured19.3Only Llama 4 Maverick measured
AIME 2025 (Artificial Analysis run)Not measured19.3%Only Llama 4 Maverick measured
LMArena Text: math14701299Kimi K2.5
LMArena Text: mathematical work14731295Kimi K2.5
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 Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
MMLU Pro85.9%79.4%Kimi K2.5
LegalBench (Vals AI)Not measured77.8%Only Llama 4 Maverick measured
CaseLaw (Vals AI)58.7%Not measuredOnly Kimi K2.5 measured
CorpFin (Vals AI)68.3%49.7%Kimi K2.5
TaxEval (Vals AI)74.2%66.6%Kimi K2.5
MortgageTax (Vals AI)66.5%58.5%Kimi K2.5
MedQA (Vals AI)94.4%43.3%Kimi K2.5
MedCode (Vals AI)39.3%36.5%Kimi K2.5
MMLU Pro (Artificial Analysis run)Not measured80.9%Only Llama 4 Maverick measured
SimpleQA Verified34.3%Not measuredOnly Kimi K2.5 measured
GeoBenchNot measured52.0%Only Llama 4 Maverick measured
LMArena Text: science14591288Kimi K2.5
LMArena Text: medicine and healthcare14481275Kimi K2.5
LMArena Text: legal and government14411286Kimi K2.5
LMArena Text: business and finance14271260Kimi K2.5
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
Design Arena: websites1249871Kimi K2.5
Design Arena: UI components1236899Kimi K2.5
Design Arena: game dev1207838Kimi K2.5
Design Arena: data viz1219882Kimi K2.5
Design Arena: 3D1205901Kimi K2.5
Design Arena: all code categories1236880Kimi K2.5
Design Arena: SVG1149Not measuredOnly Kimi K2.5 measured
Design Arena: ASCII art1165Not measuredOnly Kimi K2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index280
General benchmarks for Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
SAGE (Vals AI)49.9%35.7%Kimi K2.5
MedScribe (Vals AI)76.4%54.2%Kimi K2.5
IFBench70.2%43.0%Kimi K2.5
Long context reasoning (AA-LCR)78.0%50.0%Kimi K2.5
DTBenchNot measured61.9%Only Llama 4 Maverick measured
LMCANot measured15.9%Only Llama 4 Maverick measured
Fiction.LiveBench86.1%46.2%Kimi K2.5
Creative writing (Lech Mazur)Not measured62.0%Only Llama 4 Maverick measured
CL-bench19.3%Not measuredOnly Kimi K2.5 measured
CL-bench Life13.2%Not measuredOnly Kimi K2.5 measured
LMArena Text14451287Kimi K2.5
LMArena Text: instruction following14311267Kimi K2.5
LMArena Text: creative writing14221266Kimi K2.5
LMArena Vision12691142Kimi K2.5
LMArena Text: English14531303Kimi K2.5
LMArena Text: non-English14331269Kimi K2.5
LMArena Text: Chinese14941277Kimi K2.5
LMArena Text: German14411291Kimi K2.5
LMArena Text: Japanese14231206Kimi K2.5
LMArena Text: Korean14121203Kimi K2.5
LMArena Text: French14541259Kimi K2.5
LMArena Text: Spanish14501293Kimi K2.5
LMArena Text: Russian14351286Kimi K2.5
LMArena Text: Polish14451275Kimi K2.5
LMArena Text: multi-turn14441289Kimi K2.5
LMArena Text: longer queries14451280Kimi K2.5
LMArena Text: writing and language14251277Kimi K2.5
LMArena Text: entertainment and media14171250Kimi K2.5
LMArena Vision: English12741150Kimi K2.5
LMArena Vision: Chinese13281141Kimi K2.5
LMArena Vision: reading text12761143Kimi K2.5
LMArena Vision: humor12841100Kimi K2.5
LMArena Vision: captioning1257Not measuredOnly Kimi K2.5 measured
LMArena Vision: recognizing things1285Not measuredOnly Kimi K2.5 measured
LMArena Vision: creative writing12691099Kimi K2.5
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 Kimi K2.5 and Llama 4 Maverick
BenchmarkKimi K2.5Llama 4 MaverickLeader
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$0.0018Fits in one request
Llama 4 Maverick$0.0005Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

Kimi K2.5$0.033Fits in one request
Llama 4 Maverick$0.011Fits in one request

Llama 4 Maverick costs less

Agent loop

200K input + 10K output tokens

Kimi K2.5$0.125Fits in one request
Llama 4 Maverick$0.044Fits in one request

Llama 4 Maverick 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 Llama 4 Maverick
SpecificationMoonshotAI Kimi K2.5Meta Llama 4 Maverick
MakerMoonshot AIMeta Llama
WeightsOpen weightsOpen weights
ReleasedJanuary 27, 2026April 5, 2025
Context window262K524K
Input $/Mtok$0.50$0.1875
Output $/Mtok$2.50$0.6525
Coding index58.518.1
Independent measurements behind it22
Cost per solved task$0.24$1.491
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K2.5 better than Llama 4 Maverick for coding?

Pick Kimi K2.5 for coding: it scores 58.5 on the Vibe Coding Index against 18.1 for Llama 4 Maverick. Pick Llama 4 Maverick when output tokens cost 3.8x less, or when the context window is larger, 524K against 262K tokens.

Which is cheaper, Kimi K2.5 or Llama 4 Maverick?

Kimi K2.5 costs $0.50 per million input tokens and $2.50 per million output tokens; Llama 4 Maverick costs $0.1875 and $0.6525. Per solved SWE-bench Verified task, Kimi K2.5 costs $0.24 and Llama 4 Maverick $1.491.

Which has the bigger context window, Kimi K2.5 or Llama 4 Maverick?

Llama 4 Maverick, with 524K tokens against 262K.

How many benchmarks is the Kimi K2.5 vs Llama 4 Maverick comparison based on?

70 benchmarks have a result for both models as of October 21, 2026. Kimi K2.5's coding index rests on 2 independent benchmarks and Llama 4 Maverick'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/kimi-k2-5-vs-llama-4-maverick" title="Kimi K2.5 vs Llama 4 Maverick, 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-llama-4-maverick">LLMBenchmark.ai, Kimi K2.5 vs Llama 4 Maverick</a></p>