Kimi K2.6 vs Llama 4 Maverick
Updated October 21, 2026. 68 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Kimi K2.6 for coding: it scores 44.2 on the Vibe Coding Index against 18.1 for Llama 4 Maverick, though on 1 benchmark against 2.
Pick Llama 4 Maverick when output tokens cost 5.2x less, or when the context window is larger, 524K against 262K tokens.
- Shared results
- 68
- Kimi K2.6 only
- 41
- Llama 4 Maverick only
- 16
- 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.
Coding
Vibe Coding Index, four public coding benchmarks
Kimi K2.6
Kimi K2.6 scores 44.2 against 18.1.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Kimi K2.6
Kimi K2.6 leads, 27.0 against 9.3.
Same board, both measured
Agentic work
AA Agentic Index
Kimi K2.6
Kimi K2.6 leads, 20.5 against 0.6.
Same board, both measured
Reasoning
GPQA Diamond
Kimi K2.6
Kimi K2.6 leads, 89.1% against 69.4%.
Same board, both measured
Math
AIME
No call
Only Llama 4 Maverick has a AIME result, 25.2%.
Directional only
Knowledge
MMLU Pro
Kimi K2.6
Kimi K2.6 leads, 87.6% against 79.4%.
Same board, both measured
Web design
Design Arena: websites
Kimi K2.6
Kimi K2.6 leads, 1269 against 871.
Same board, both measured
Long documents
Listed context window
Llama 4 Maverick
Llama 4 Maverick takes 524K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Maverick
Kimi K2.6 $0.0024, Llama 4 Maverick $0.0005 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2.6
Kimi K2.6 $0.35, Llama 4 Maverick $1.491.
Published attempt cost and pass rate
At a glance
- Coding index
- Kimi K2.6 44.2 from 1 benchmark, Llama 4 Maverick 18.1 from 2 benchmarks.
- Widest category
- Agentic work, 49.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- τ²-Bench Telecom: Kimi K2.6 95.9% against Llama 4 Maverick 17.8%, 78.1 points apart on a 0 to 100 scale.
- Output price
- Kimi K2.6 $3.41 against Llama 4 Maverick $0.6525 per million output tokens, 5.2x apart.
- Context window
- Kimi K2.6 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.
| Category | Kimi K2.6 | Bars | Llama 4 Maverick | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 9 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 10 | 0 | ||
| Web design | 6 | 0 | ||
| General | 29 | 0 | ||
| All shared boards | 68 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index80
| Benchmark | Kimi K2.6 | Llama 4 Maverick | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 15.6% | Only Llama 4 Maverick measured |
| SWE-bench Verified | Not measured | 21.0% | Only Llama 4 Maverick measured |
| LMArena WebDev | 1509 | Not measured | Only Kimi K2.6 measured |
| AA Coding Index | 61.8 | 16.3 | Kimi K2.6 |
| LiveCodeBench (Vals AI) | 86.8% | 47.3% | Kimi K2.6 |
| SWE-bench Verified (Vals AI) | 76.2% | Not measured | Only Kimi K2.6 measured |
| Vibe Code Bench (Vals AI) | 37.9% | Not measured | Only Kimi K2.6 measured |
| Code migration (Vals AI) | 27.8% | Not measured | Only Kimi K2.6 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Kimi K2.6 measured |
| Terminal-Bench 2.1 (Vals AI) | 53.6% | Not measured | Only Kimi K2.6 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 39.7% | Only Llama 4 Maverick measured |
| SciCode | 51.5% | 31.7% | Kimi K2.6 |
| Terminal-Bench Hard (Artificial Analysis run) | 43.9% | 6.8% | Kimi K2.6 |
| WeirdML | 55.9% | 24.5% | Kimi K2.6 |
| ALE-Bench | 1092.7 | 173.0 | Kimi K2.6 |
| LMArena Text: coding | 1489 | 1301 | Kimi K2.6 |
| LMArena Text: software and IT | 1484 | 1299 | Kimi K2.6 |
| LMArena WebDev: React | 1505 | Not measured | Only Kimi K2.6 measured |
| LMArena WebDev: HTML | 1485 | Not measured | Only Kimi K2.6 measured |
| LMArena WebDev: from an image | 1521 | Not measured | Only Kimi K2.6 measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2.6 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AA Intelligence Index | 27.0 | 9.3 | Kimi K2.6 |
| Epoch Capabilities Index | 150.9 | 132.2 | Kimi K2.6 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2.6 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AA Agentic Index | 20.5 | 0.6 | Kimi K2.6 |
| Design Arena: agents building web apps | 1268 | Not measured | Only Kimi K2.6 measured |
| Design Arena: agents building full-stack apps | 1155 | Not measured | Only Kimi K2.6 measured |
| Design Arena: agents building mobile apps | 1156 | Not measured | Only Kimi K2.6 measured |
| Design Arena: agents building Android apps | 1166 | Not measured | Only Kimi K2.6 measured |
| Design Arena: agents building Godot games | 1120 | Not measured | Only Kimi K2.6 measured |
| Design Arena: agents building games | 1141 | Not measured | Only Kimi K2.6 measured |
| Design Arena: HTML slides | 1184 | Not measured | Only Kimi K2.6 measured |
| Design Arena: PowerPoint slides | 1128 | Not measured | Only Kimi K2.6 measured |
| Design Arena: spreadsheets | 1276 | Not measured | Only Kimi K2.6 measured |
| Finance Agent (Vals AI) | 44.9% | Not measured | Only Kimi K2.6 measured |
| Tax Agent Bench (Vals AI) | 12.4% | Not measured | Only Kimi K2.6 measured |
| Legal Research Bench (Vals AI) | 15.9% | Not measured | Only Kimi K2.6 measured |
| Excel Modeling Benchmark (Vals AI) | 57.9% | Not measured | Only Kimi K2.6 measured |
| τ²-Bench Telecom | 95.9% | 17.8% | Kimi K2.6 |
| OSWorld 2.0 | 4.6% | Not measured | Only Kimi K2.6 measured |
| Vending-Bench 2 | $6,205 | Not measured | Only Kimi K2.6 measured |
| Neither model has a result on the other 22 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | Kimi K2.6 | Llama 4 Maverick | Leader |
|---|---|---|---|
| GPQA Diamond | 89.1% | 69.4% | Kimi K2.6 |
| MMMU Pro (Vals AI) | 86.3% | 71.7% | Kimi K2.6 |
| GPQA Diamond (Artificial Analysis run) | 91.1% | 67.1% | Kimi K2.6 |
| Humanity's Last Exam (Artificial Analysis run) | 37.5% | 4.9% | Kimi K2.6 |
| GPQA Diamond (Epoch AI run) | 90.8% | Not measured | Only Kimi K2.6 measured |
| ARC-AGI | Not measured | 4.4% | Only Llama 4 Maverick measured |
| ARC-AGI-2 | Not measured | 0.0% | Only Llama 4 Maverick measured |
| SimpleBench | Not measured | 27.7% | Only Llama 4 Maverick measured |
| Chess puzzles | 20.0% | Not measured | Only Kimi K2.6 measured |
| Mystery game puzzles | 18.0% | Not measured | Only Kimi K2.6 measured |
| EBR-bench | 2.4% | Not measured | Only Kimi K2.6 measured |
| LMArena Text: hard prompts | 1470 | 1281 | Kimi K2.6 |
| LMArena Text: expert | 1491 | 1259 | Kimi K2.6 |
| LMArena Text: hard prompts in English | 1471 | 1295 | Kimi K2.6 |
| LMArena Vision: diagrams | 1298 | 1134 | Kimi K2.6 |
| LMArena Vision: homework | 1310 | 1164 | Kimi K2.6 |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2.6 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AIME | Not measured | 25.2% | Only Llama 4 Maverick measured |
| MATH 500 (Vals AI) | Not measured | 85.2% | Only Llama 4 Maverick measured |
| MGSM (Vals AI) | Not measured | 92.4% | Only Llama 4 Maverick measured |
| AA Math Index | Not measured | 19.3 | Only Llama 4 Maverick measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 19.3% | Only Llama 4 Maverick measured |
| OTIS Mock AIME | 96.1% | Not measured | Only Kimi K2.6 measured |
| FrontierMath, tiers 1 to 3 | 57.2% | Not measured | Only Kimi K2.6 measured |
| FrontierMath, tier 4 | 25.6% | Not measured | Only Kimi K2.6 measured |
| ProofBench | 16.0% | Not measured | Only Kimi K2.6 measured |
| LMArena Text: math | 1474 | 1299 | Kimi K2.6 |
| LMArena Text: mathematical work | 1480 | 1295 | Kimi K2.6 |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
| Benchmark | Kimi K2.6 | Llama 4 Maverick | Leader |
|---|---|---|---|
| MMLU Pro | 87.6% | 79.4% | Kimi K2.6 |
| LegalBench (Vals AI) | 84.7% | 77.8% | Kimi K2.6 |
| CaseLaw (Vals AI) | 61.2% | Not measured | Only Kimi K2.6 measured |
| CorpFin (Vals AI) | 66.7% | 49.7% | Kimi K2.6 |
| TaxEval (Vals AI) | 74.7% | 66.6% | Kimi K2.6 |
| MortgageTax (Vals AI) | 65.8% | 58.5% | Kimi K2.6 |
| MedQA (Vals AI) | Not measured | 43.3% | Only Llama 4 Maverick measured |
| MedCode (Vals AI) | 40.1% | 36.5% | Kimi K2.6 |
| MMLU Pro (Artificial Analysis run) | Not measured | 80.9% | Only Llama 4 Maverick measured |
| SimpleQA Verified | 34.9% | Not measured | Only Kimi K2.6 measured |
| GeoBench | Not measured | 52.0% | Only Llama 4 Maverick measured |
| LMArena Text: science | 1468 | 1288 | Kimi K2.6 |
| LMArena Text: medicine and healthcare | 1457 | 1275 | Kimi K2.6 |
| LMArena Text: legal and government | 1462 | 1286 | Kimi K2.6 |
| LMArena Text: business and finance | 1445 | 1260 | Kimi K2.6 |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Kimi K2.6 | Llama 4 Maverick | Leader |
|---|---|---|---|
| Design Arena: websites | 1269 | 871 | Kimi K2.6 |
| Design Arena: UI components | 1266 | 899 | Kimi K2.6 |
| Design Arena: game dev | 1251 | 838 | Kimi K2.6 |
| Design Arena: data viz | 1249 | 882 | Kimi K2.6 |
| Design Arena: 3D | 1268 | 901 | Kimi K2.6 |
| Design Arena: all code categories | 1272 | 880 | Kimi K2.6 |
| Design Arena: SVG | 1181 | Not measured | Only Kimi K2.6 measured |
| Design Arena: ASCII art | 1164 | Not measured | Only Kimi K2.6 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index290
| Benchmark | Kimi K2.6 | Llama 4 Maverick | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 56.6% | Not measured | Only Kimi K2.6 measured |
| SAGE (Vals AI) | 50.2% | 35.7% | Kimi K2.6 |
| MedScribe (Vals AI) | 78.2% | 54.2% | Kimi K2.6 |
| Vals Multimodal Index | 56.4% | Not measured | Only Kimi K2.6 measured |
| IFBench | 76.0% | 43.0% | Kimi K2.6 |
| Long context reasoning (AA-LCR) | 81.0% | 50.0% | Kimi K2.6 |
| DTBench | 90.9% | 61.9% | Kimi K2.6 |
| LMCA | 37.3% | 15.9% | Kimi K2.6 |
| Fiction.LiveBench | Not measured | 46.2% | Only Llama 4 Maverick measured |
| Creative writing (Lech Mazur) | Not measured | 62.0% | Only Llama 4 Maverick measured |
| Furniture assembly | 21.7% | Not measured | Only Kimi K2.6 measured |
| ExploitBench | 18.4% | Not measured | Only Kimi K2.6 measured |
| LMArena Text | 1455 | 1287 | Kimi K2.6 |
| LMArena Text: instruction following | 1451 | 1267 | Kimi K2.6 |
| LMArena Text: creative writing | 1434 | 1266 | Kimi K2.6 |
| LMArena Vision | 1282 | 1142 | Kimi K2.6 |
| LMArena Text: English | 1460 | 1303 | Kimi K2.6 |
| LMArena Text: non-English | 1446 | 1269 | Kimi K2.6 |
| LMArena Text: Chinese | 1520 | 1277 | Kimi K2.6 |
| LMArena Text: German | 1451 | 1291 | Kimi K2.6 |
| LMArena Text: Japanese | 1443 | 1206 | Kimi K2.6 |
| LMArena Text: Korean | 1427 | 1203 | Kimi K2.6 |
| LMArena Text: French | 1471 | 1259 | Kimi K2.6 |
| LMArena Text: Spanish | 1464 | 1293 | Kimi K2.6 |
| LMArena Text: Russian | 1446 | 1286 | Kimi K2.6 |
| LMArena Text: Polish | 1438 | 1275 | Kimi K2.6 |
| LMArena Text: multi-turn | 1453 | 1289 | Kimi K2.6 |
| LMArena Text: longer queries | 1468 | 1280 | Kimi K2.6 |
| LMArena Text: writing and language | 1439 | 1277 | Kimi K2.6 |
| LMArena Text: entertainment and media | 1428 | 1250 | Kimi K2.6 |
| LMArena Vision: English | 1287 | 1150 | Kimi K2.6 |
| LMArena Vision: Chinese | 1346 | 1141 | Kimi K2.6 |
| LMArena Vision: reading text | 1291 | 1143 | Kimi K2.6 |
| LMArena Vision: humor | 1280 | 1100 | Kimi K2.6 |
| LMArena Vision: creative writing | 1273 | 1099 | Kimi K2.6 |
| LMArena Document | 1451 | Not measured | Only Kimi K2.6 measured |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2.6 | Llama 4 Maverick | 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
Llama 4 Maverick costs less
Repository review
50K input + 3K output tokens
Llama 4 Maverick costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | MoonshotAI Kimi K2.6 | Meta Llama 4 Maverick |
|---|---|---|
| Maker | Moonshot AI | Meta Llama |
| Weights | Open weights | Open weights |
| Released | April 20, 2026 | April 5, 2025 |
| Context window | 262K | 524K |
| Input $/Mtok | $0.65 | $0.1875 |
| Output $/Mtok | $3.41 | $0.6525 |
| Coding index | 44.2 | 18.1 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $0.35 | $1.491 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K2.6 better than Llama 4 Maverick for coding?
Pick Kimi K2.6 for coding: it scores 44.2 on the Vibe Coding Index against 18.1 for Llama 4 Maverick, though on 1 benchmark against 2. Pick Llama 4 Maverick when output tokens cost 5.2x less, or when the context window is larger, 524K against 262K tokens.
Which is cheaper, Kimi K2.6 or Llama 4 Maverick?
Kimi K2.6 costs $0.65 per million input tokens and $3.41 per million output tokens; Llama 4 Maverick costs $0.1875 and $0.6525. Per solved SWE-bench Verified task, Kimi K2.6 costs $0.35 and Llama 4 Maverick $1.491.
Which has the bigger context window, Kimi K2.6 or Llama 4 Maverick?
Llama 4 Maverick, with 524K tokens against 262K.
How many benchmarks is the Kimi K2.6 vs Llama 4 Maverick comparison based on?
68 benchmarks have a result for both models as of October 21, 2026. Kimi K2.6's coding index rests on 1 independent benchmark and Llama 4 Maverick's on 2. Where only one model has a result, the page says so instead of naming a winner.