Claude Opus 4.6 vs Kimi K2.6
Updated October 21, 2026. 90 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Claude Opus 4.6 for coding: it scores 66.9 on the Vibe Coding Index against 44.2 for Kimi K2.6.
Pick Kimi K2.6 when output tokens cost 7.3x less, or when a solved task costs $0.35 against $1.56.
- Shared results
- 90
- Claude Opus 4.6 only
- 18
- Kimi K2.6 only
- 19
- 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
Claude Opus 4.6
Claude Opus 4.6 scores 66.9 against 44.2.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Opus 4.6
Claude Opus 4.6 leads, 31.9 against 27.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Kimi K2.6 has a AA Agentic Index result, 20.5.
Directional only
Reasoning
GPQA Diamond
Claude Opus 4.6
Claude Opus 4.6 leads, 89.7% against 89.1%.
Same board, both measured
Math
AIME
No call
Only Claude Opus 4.6 has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Claude Opus 4.6
Claude Opus 4.6 leads, 89.1% against 87.6%.
Same board, both measured
Web design
Design Arena: websites
Claude Opus 4.6
Claude Opus 4.6 leads, 1291 against 1269.
Same board, both measured
Long documents
Listed context window
Claude Opus 4.6
Claude Opus 4.6 takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2.6
Claude Opus 4.6 $0.018, Kimi K2.6 $0.0024 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2.6
Claude Opus 4.6 $1.56, Kimi K2.6 $0.35.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.6 66.9 from 2 benchmarks, Kimi K2.6 44.2 from 1 benchmark.
- Widest category
- Math, 10.1 points apart on average over 6 shared benchmarks.
- Widest single gap
- ProofBench: Claude Opus 4.6 50.0% against Kimi K2.6 16.0%, 34.0 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.6 $25.00 against Kimi K2.6 $3.41 per million output tokens, 7.3x apart.
- Context window
- Claude Opus 4.6 takes 1M tokens, Kimi K2.6 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.
| Category | Claude Opus 4.6 | Bars | Kimi K2.6 | Ties |
|---|---|---|---|---|
| Coding | 10 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 2 | ||
| Reasoning | 10 | 3 | ||
| Math | 5 | 1 | ||
| Knowledge | 12 | 0 | ||
| Web design | 8 | 0 | ||
| General | 29 | 2 | ||
| All shared boards | 81 | 9 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index101
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | Leader |
|---|---|---|---|
| SWE-bench Verified | 75.6% | Not measured | Only Claude Opus 4.6 measured |
| SWE-bench Multilingual | 72.0% | Not measured | Only Claude Opus 4.6 measured |
| LMArena WebDev | 1547 | 1509 | Claude Opus 4.6 |
| AA Coding Index | Not measured | 61.8 | Only Kimi K2.6 measured |
| LiveCodeBench (Vals AI) | 84.7% | 86.8% | Kimi K2.6 |
| SWE-bench Verified (Vals AI) | 78.2% | 76.2% | Claude Opus 4.6 |
| Vibe Code Bench (Vals AI) | 57.6% | 37.9% | Claude Opus 4.6 |
| Code migration (Vals AI) | Not measured | 27.8% | Only Kimi K2.6 measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Kimi K2.6 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 53.6% | Only Kimi K2.6 measured |
| SciCode | Not measured | 51.5% | Only Kimi K2.6 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 48.5% | 43.9% | Claude Opus 4.6 |
| Terminal-Bench | 79.8% | Not measured | Only Claude Opus 4.6 measured |
| FrontierCode | 26.6% | Not measured | Only Claude Opus 4.6 measured |
| GSO-Bench | 41.2% | Not measured | Only Claude Opus 4.6 measured |
| WeirdML | 78.0% | 55.9% | Claude Opus 4.6 |
| Cybench | 93.0% | Not measured | Only Claude Opus 4.6 measured |
| ALE-Bench | Not measured | 1092.7 | Only Kimi K2.6 measured |
| LMArena Text: coding | 1534 | 1489 | Claude Opus 4.6 |
| LMArena Text: software and IT | 1527 | 1484 | Claude Opus 4.6 |
| LMArena WebDev: React | 1539 | 1505 | Claude Opus 4.6 |
| LMArena WebDev: HTML | 1559 | 1485 | Claude Opus 4.6 |
| LMArena WebDev: from an image | 1543 | 1521 | Claude Opus 4.6 |
| Neither model has a result on the other 15 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | Leader |
|---|---|---|---|
| AA Intelligence Index | 31.9 | 27.0 | Claude Opus 4.6 |
| Epoch Capabilities Index | 155.7 | 150.9 | Claude Opus 4.6 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index52
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 20.5 | Only Kimi K2.6 measured |
| Design Arena: agents building web apps | 1206 | 1268 | Kimi K2.6 |
| Design Arena: agents building full-stack apps | 1220 | 1155 | Claude Opus 4.6 |
| Design Arena: agents building mobile apps | 1207 | 1156 | Claude Opus 4.6 |
| Design Arena: agents building Android apps | 1204 | 1166 | Claude Opus 4.6 |
| Design Arena: agents building Godot games | Not measured | 1120 | Only Kimi K2.6 measured |
| Design Arena: agents building games | 1214 | 1141 | Claude Opus 4.6 |
| Design Arena: HTML slides | Not measured | 1184 | Only Kimi K2.6 measured |
| Design Arena: PowerPoint slides | Not measured | 1128 | Only Kimi K2.6 measured |
| Design Arena: spreadsheets | Not measured | 1276 | Only Kimi K2.6 measured |
| Finance Agent (Vals AI) | Not measured | 44.9% | Only Kimi K2.6 measured |
| Tax Agent Bench (Vals AI) | Not measured | 12.4% | Only Kimi K2.6 measured |
| Legal Research Bench (Vals AI) | Not measured | 15.9% | Only Kimi K2.6 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 57.9% | Only Kimi K2.6 measured |
| τ²-Bench Telecom | 92.1% | 95.9% | Kimi K2.6 |
| APEX-Agents | 46.3% | Not measured | Only Claude Opus 4.6 measured |
| METR time horizons | 78.9% | Not measured | Only Claude Opus 4.6 measured |
| Remote Labor Index | 4.2% | Not measured | Only Claude Opus 4.6 measured |
| OSWorld 2.0 | Not measured | 4.6% | Only Kimi K2.6 measured |
| DeepResearch Bench | 55.3% | Not measured | Only Claude Opus 4.6 measured |
| Vending-Bench 2 | $8,018 | $6,205 | Claude Opus 4.6 |
| Neither model has a result on the other 18 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index103
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | Leader |
|---|---|---|---|
| GPQA Diamond | 89.7% | 89.1% | Claude Opus 4.6 |
| MMMU Pro (Vals AI) | 83.9% | 86.3% | Kimi K2.6 |
| GPQA Diamond (Artificial Analysis run) | 89.6% | 91.1% | Kimi K2.6 |
| Humanity's Last Exam (Artificial Analysis run) | 39.9% | 37.5% | Claude Opus 4.6 |
| GPQA Diamond (Epoch AI run) | 90.5% | 90.8% | Kimi K2.6 |
| ARC-AGI | 94.0% | Not measured | Only Claude Opus 4.6 measured |
| ARC-AGI-2 | 69.2% | Not measured | Only Claude Opus 4.6 measured |
| SimpleBench | 67.6% | Not measured | Only Claude Opus 4.6 measured |
| Chess puzzles | 21.0% | 20.0% | Claude Opus 4.6 |
| Mystery game puzzles | 25.0% | 18.0% | Claude Opus 4.6 |
| EBR-bench | 12.7% | 2.4% | Claude Opus 4.6 |
| LMArena Text: hard prompts | 1525 | 1470 | Claude Opus 4.6 |
| LMArena Text: expert | 1544 | 1491 | Claude Opus 4.6 |
| LMArena Text: hard prompts in English | 1530 | 1471 | Claude Opus 4.6 |
| LMArena Vision: diagrams | 1340 | 1298 | Claude Opus 4.6 |
| LMArena Vision: homework | 1337 | 1310 | Claude Opus 4.6 |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | Leader |
|---|---|---|---|
| AIME | 95.6% | Not measured | Only Claude Opus 4.6 measured |
| OTIS Mock AIME | 94.4% | 96.1% | Kimi K2.6 |
| FrontierMath, tiers 1 to 3 | 66.0% | 57.2% | Claude Opus 4.6 |
| FrontierMath, tier 4 | 26.8% | 25.6% | Claude Opus 4.6 |
| ProofBench | 50.0% | 16.0% | Claude Opus 4.6 |
| LMArena Text: math | 1518 | 1474 | Claude Opus 4.6 |
| LMArena Text: mathematical work | 1525 | 1480 | Claude Opus 4.6 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index120
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | Leader |
|---|---|---|---|
| MMLU Pro | 89.1% | 87.6% | Claude Opus 4.6 |
| LegalBench (Vals AI) | 85.3% | 84.7% | Claude Opus 4.6 |
| CaseLaw (Vals AI) | 62.1% | 61.2% | Claude Opus 4.6 |
| CorpFin (Vals AI) | 67.0% | 66.7% | Claude Opus 4.6 |
| TaxEval (Vals AI) | 76.0% | 74.7% | Claude Opus 4.6 |
| MortgageTax (Vals AI) | 68.5% | 65.8% | Claude Opus 4.6 |
| MedQA (Vals AI) | 95.4% | Not measured | Only Claude Opus 4.6 measured |
| MedCode (Vals AI) | 49.1% | 40.1% | Claude Opus 4.6 |
| SimpleQA Verified | 47.0% | 34.9% | Claude Opus 4.6 |
| LMArena Text: science | 1519 | 1468 | Claude Opus 4.6 |
| LMArena Text: medicine and healthcare | 1504 | 1457 | Claude Opus 4.6 |
| LMArena Text: legal and government | 1512 | 1462 | Claude Opus 4.6 |
| LMArena Text: business and finance | 1497 | 1445 | Claude Opus 4.6 |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | Leader |
|---|---|---|---|
| Design Arena: websites | 1291 | 1269 | Claude Opus 4.6 |
| Design Arena: UI components | 1284 | 1266 | Claude Opus 4.6 |
| Design Arena: game dev | 1278 | 1251 | Claude Opus 4.6 |
| Design Arena: data viz | 1279 | 1249 | Claude Opus 4.6 |
| Design Arena: 3D | 1274 | 1268 | Claude Opus 4.6 |
| Design Arena: all code categories | 1289 | 1272 | Claude Opus 4.6 |
| Design Arena: SVG | 1227 | 1181 | Claude Opus 4.6 |
| Design Arena: ASCII art | 1254 | 1164 | Claude Opus 4.6 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index292
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 56.6% | Only Kimi K2.6 measured |
| SAGE (Vals AI) | 51.6% | 50.2% | Claude Opus 4.6 |
| MedScribe (Vals AI) | 86.7% | 78.2% | Claude Opus 4.6 |
| Vals Multimodal Index | Not measured | 56.4% | Only Kimi K2.6 measured |
| IFBench | 53.1% | 76.0% | Kimi K2.6 |
| Long context reasoning (AA-LCR) | 78.0% | 81.0% | Kimi K2.6 |
| DTBench | 91.2% | 90.9% | Claude Opus 4.6 |
| LMCA | 55.8% | 37.3% | Claude Opus 4.6 |
| CL-bench | 20.7% | Not measured | Only Claude Opus 4.6 measured |
| Furniture assembly | 28.3% | 21.7% | Claude Opus 4.6 |
| ExploitBench | Not measured | 18.4% | Only Kimi K2.6 measured |
| CL-bench Life | 17.0% | Not measured | Only Claude Opus 4.6 measured |
| LMArena Text | 1501 | 1455 | Claude Opus 4.6 |
| LMArena Text: instruction following | 1521 | 1451 | Claude Opus 4.6 |
| LMArena Text: creative writing | 1505 | 1434 | Claude Opus 4.6 |
| LMArena Vision | 1316 | 1282 | Claude Opus 4.6 |
| LMArena Text: English | 1511 | 1460 | Claude Opus 4.6 |
| LMArena Text: non-English | 1488 | 1446 | Claude Opus 4.6 |
| LMArena Text: Chinese | 1551 | 1520 | Claude Opus 4.6 |
| LMArena Text: German | 1500 | 1451 | Claude Opus 4.6 |
| LMArena Text: Japanese | 1488 | 1443 | Claude Opus 4.6 |
| LMArena Text: Korean | 1464 | 1427 | Claude Opus 4.6 |
| LMArena Text: French | 1512 | 1471 | Claude Opus 4.6 |
| LMArena Text: Spanish | 1510 | 1464 | Claude Opus 4.6 |
| LMArena Text: Russian | 1497 | 1446 | Claude Opus 4.6 |
| LMArena Text: Polish | 1499 | 1438 | Claude Opus 4.6 |
| LMArena Text: multi-turn | 1511 | 1453 | Claude Opus 4.6 |
| LMArena Text: longer queries | 1518 | 1468 | Claude Opus 4.6 |
| LMArena Text: writing and language | 1502 | 1439 | Claude Opus 4.6 |
| LMArena Text: entertainment and media | 1492 | 1428 | Claude Opus 4.6 |
| LMArena Vision: English | 1324 | 1287 | Claude Opus 4.6 |
| LMArena Vision: Chinese | 1370 | 1346 | Claude Opus 4.6 |
| LMArena Vision: reading text | 1326 | 1291 | Claude Opus 4.6 |
| LMArena Vision: humor | 1314 | 1280 | Claude Opus 4.6 |
| LMArena Vision: recognizing things | 1274 | Not measured | Only Claude Opus 4.6 measured |
| LMArena Vision: creative writing | 1331 | 1273 | Claude Opus 4.6 |
| LMArena Document | 1507 | 1451 | Claude Opus 4.6 |
| Neither model has a result on the other 9 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.6 | Kimi K2.6 | 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 K2.6 costs less
Repository review
50K input + 3K output tokens
Kimi K2.6 costs less
Agent loop
200K input + 10K output tokens
Kimi K2.6 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 | Anthropic Claude Opus 4.6 | MoonshotAI Kimi K2.6 |
|---|---|---|
| Maker | Anthropic | Moonshot AI |
| Weights | No public weights listed | Open weights |
| Released | February 4, 2026 | April 20, 2026 |
| Context window | 1M | 262K |
| Input $/Mtok | $5.00 | $0.65 |
| Output $/Mtok | $25.00 | $3.41 |
| Coding index | 66.9 | 44.2 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $1.56 | $0.35 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.6 better than Kimi K2.6 for coding?
Pick Claude Opus 4.6 for coding: it scores 66.9 on the Vibe Coding Index against 44.2 for Kimi K2.6. Pick Kimi K2.6 when output tokens cost 7.3x less, or when a solved task costs $0.35 against $1.56.
Which is cheaper, Claude Opus 4.6 or Kimi K2.6?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Kimi K2.6 costs $0.65 and $3.41. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and Kimi K2.6 $0.35.
Which has the bigger context window, Claude Opus 4.6 or Kimi K2.6?
Claude Opus 4.6, with 1M tokens against 262K.
How many benchmarks is the Claude Opus 4.6 vs Kimi K2.6 comparison based on?
90 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.6's coding index rests on 2 independent benchmarks and Kimi K2.6's on 1. Where only one model has a result, the page says so instead of naming a winner.