Claude Opus 4.7 vs Kimi K3
Updated October 21, 2026. 79 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 K3 for coding: it scores 61.8 on the Vibe Coding Index against 51.1 for Claude Opus 4.7.
Pick Claude Opus 4.7 when what matters is Code migration (Vals AI) or LMArena Text: coding, where it leads.
- Shared results
- 79
- Claude Opus 4.7 only
- 22
- Kimi K3 only
- 38
- Like-for-like categories
- 7 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 K3
Kimi K3 scores 61.8 against 51.1.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Kimi K3
Kimi K3 leads, 43.6 against 40.7.
Same board, both measured
Agentic work
AA Agentic Index
Kimi K3
Kimi K3 leads, 50.0 against 38.6.
Same board, both measured
Reasoning
GPQA Diamond
Kimi K3
Kimi K3 leads, 92.9% against 90.2%.
Same board, both measured
Math
AIME
No call
Only Claude Opus 4.7 has a AIME result, 96.3%.
Directional only
Knowledge
MMLU Pro
Claude Opus 4.7
Claude Opus 4.7 leads, 89.9% against 88.0%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Kimi K3 has a Design Arena: websites result, 1336.
Directional only
General
Vals Index
No call
Only Kimi K3 has a Vals Index result, 53.0%.
Directional only
Long documents
Listed context window
Kimi K3
Kimi K3 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K3
Claude Opus 4.7 $0.018, Kimi K3 $0.0062 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K3
Claude Opus 4.7 $2.95, Kimi K3 $0.81.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.7 51.1 from 1 benchmark, Kimi K3 61.8 from 2 benchmarks.
- Widest category
- Agentic work, 9.3 points apart on average over 8 shared benchmarks.
- Widest single gap
- Vending-Bench 2: Claude Opus 4.7 $10,937 against Kimi K3 $5,165, 36.1 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.7 $25.00 against Kimi K3 $11.936 per million output tokens, 2.1x apart.
- Context window
- Claude Opus 4.7 takes 1M tokens, Kimi K3 1.05M.
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 4.7 | Bars | Kimi K3 | Ties |
|---|---|---|---|---|
| Coding | 3 | 12 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 2 | 6 | ||
| Reasoning | 7 | 6 | ||
| Math | 3 | 3 | ||
| Knowledge | 7 | 4 | ||
| General | 18 | 6 | ||
| All shared boards | 40 | 39 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index312
| Benchmark | Claude Opus 4.7 | Kimi K3 | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 59.3% | Only Kimi K3 measured |
| LMArena WebDev | 1558 | 1655 | Kimi K3 |
| AA Coding Index | 73.6 | 76.2 | Kimi K3 |
| LiveCodeBench (Vals AI) | 85.1% | 87.2% | Kimi K3 |
| SWE-bench Verified (Vals AI) | 82.0% | 93.4% | Kimi K3 |
| Terminal-Bench 4 (Vals AI) | Not measured | 17.2% | Only Kimi K3 measured |
| Vibe Code Bench (Vals AI) | 71.0% | 85.0% | Kimi K3 |
| Code migration (Vals AI) | 43.9% | 16.1% | Claude Opus 4.7 |
| ProgramBench (Vals AI) | 0.0% | 2.0% | Kimi K3 |
| IOI (Vals AI) | Not measured | 48.9% | Only Kimi K3 measured |
| Terminal-Bench 2.1 (Vals AI) | 68.5% | 80.9% | Kimi K3 |
| SWE-bench Multimodal (Vals AI) | Not measured | 44.2% | Only Kimi K3 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 18.2% | Only Kimi K3 measured |
| CyberBench (Vals AI) | Not measured | 75.2% | Only Kimi K3 measured |
| SciCode | Not measured | 59.5% | Only Kimi K3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 54.5% | Not measured | Only Claude Opus 4.7 measured |
| Terminal-Bench | 80.2% | Not measured | Only Claude Opus 4.7 measured |
| FrontierCode | 38.5% | 44.2% | Kimi K3 |
| FrontierSWE | Not measured | 25.9% | Only Kimi K3 measured |
| GSO-Bench | 44.1% | Not measured | Only Claude Opus 4.7 measured |
| WeirdML | 76.4% | 82.6% | Kimi K3 |
| MirrorCode | 31.1% | Not measured | Only Claude Opus 4.7 measured |
| ALE-Bench | Not measured | 1524.5 | Only Kimi K3 measured |
| LMArena Text: coding | 1519 | 1508 | Claude Opus 4.7 |
| LMArena Text: software and IT | 1516 | 1499 | Claude Opus 4.7 |
| LMArena WebDev: React | 1560 | 1670 | Kimi K3 |
| LMArena WebDev: HTML | 1554 | 1644 | Kimi K3 |
| LMArena WebDev: from an image | 1577 | 1579 | Kimi K3 |
| Neither model has a result on the other 10 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Opus 4.7 | Kimi K3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 40.7 | 43.6 | Kimi K3 |
| Epoch Capabilities Index | 156.8 | 157.9 | Kimi K3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index26
| Benchmark | Claude Opus 4.7 | Kimi K3 | Leader |
|---|---|---|---|
| AA Agentic Index | 38.6 | 50.0 | Kimi K3 |
| Design Arena: agents building web apps | Not measured | 1296 | Only Kimi K3 measured |
| Design Arena: agents building full-stack apps | Not measured | 1315 | Only Kimi K3 measured |
| Design Arena: agents building mobile apps | Not measured | 1267 | Only Kimi K3 measured |
| Design Arena: agents building Android apps | Not measured | 1256 | Only Kimi K3 measured |
| Design Arena: agents building Godot games | Not measured | 1223 | Only Kimi K3 measured |
| Design Arena: agents building games | Not measured | 1252 | Only Kimi K3 measured |
| Design Arena: HTML slides | Not measured | 1256 | Only Kimi K3 measured |
| Design Arena: PowerPoint slides | Not measured | 1273 | Only Kimi K3 measured |
| Design Arena: spreadsheets | Not measured | 1058 | Only Kimi K3 measured |
| LiveBench research | Not measured | 79.0% | Only Kimi K3 measured |
| LiveBench browser | Not measured | 16.0% | Only Kimi K3 measured |
| LiveBench long agentic | Not measured | 42.8% | Only Kimi K3 measured |
| Finance Agent (Vals AI) | 51.5% | 53.1% | Kimi K3 |
| Tax Agent Bench (Vals AI) | 23.7% | 33.4% | Kimi K3 |
| Legal Research Bench (Vals AI) | 38.5% | 46.1% | Kimi K3 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 12.9% | Only Kimi K3 measured |
| Excel Modeling Benchmark (Vals AI) | 63.7% | 66.7% | Kimi K3 |
| BioMysteryBench (Vals AI) | Not measured | 72.6% | Only Kimi K3 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 1.4% | Only Kimi K3 measured |
| Time Horizon Index (Vals AI) | Not measured | 10.5% | Only Kimi K3 measured |
| τ²-Bench Telecom | 88.6% | Not measured | Only Claude Opus 4.7 measured |
| APEX-Agents | 49.2% | 47.8% | Claude Opus 4.7 |
| OSWorld 2.0 | 18.2% | Not measured | Only Claude Opus 4.7 measured |
| PostTrainBench | 28.6% | 32.0% | Kimi K3 |
| Vending-Bench 2 | $10,937 | $5,165 | Claude Opus 4.7 |
| LMArena Search | 1230 | Not measured | Only Claude Opus 4.7 measured |
| Neither model has a result on the other 12 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index76
| Benchmark | Claude Opus 4.7 | Kimi K3 | Leader |
|---|---|---|---|
| GPQA Diamond | 90.2% | 92.9% | Kimi K3 |
| LiveBench reasoning | Not measured | 90.7% | Only Kimi K3 measured |
| MMMU Pro (Vals AI) | 85.5% | 88.2% | Kimi K3 |
| GPQA Diamond (Artificial Analysis run) | 91.4% | 93.5% | Kimi K3 |
| Humanity's Last Exam (Artificial Analysis run) | 42.3% | 46.9% | Kimi K3 |
| GPQA Diamond (Epoch AI run) | 90.2% | 93.1% | Kimi K3 |
| ARC-AGI | 93.5% | 94.5% | Kimi K3 |
| ARC-AGI-2 | 75.8% | 60.4% | Claude Opus 4.7 |
| SimpleBench | 61.7% | 60.7% | Claude Opus 4.7 |
| Chess puzzles | 41.0% | 37.0% | Claude Opus 4.7 |
| Mystery game puzzles | 28.0% | 26.0% | Claude Opus 4.7 |
| EBR-bench | 19.0% | Not measured | Only Claude Opus 4.7 measured |
| LMArena Text: hard prompts | 1506 | 1495 | Claude Opus 4.7 |
| LMArena Text: expert | 1521 | 1520 | Claude Opus 4.7 |
| LMArena Text: hard prompts in English | 1508 | 1496 | Claude Opus 4.7 |
| LMArena Vision: diagrams | 1336 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: homework | 1337 | Not measured | Only Claude Opus 4.7 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | Claude Opus 4.7 | Kimi K3 | Leader |
|---|---|---|---|
| AIME | 96.3% | Not measured | Only Claude Opus 4.7 measured |
| OTIS Mock AIME | 97.8% | 97.2% | Claude Opus 4.7 |
| FrontierMath, tiers 1 to 3 | 70.2% | 72.2% | Kimi K3 |
| FrontierMath, tier 4 | 31.7% | 39.0% | Kimi K3 |
| ProofBench | 54.0% | 87.0% | Kimi K3 |
| LMArena Text: math | 1498 | 1494 | Claude Opus 4.7 |
| LMArena Text: mathematical work | 1509 | 1505 | Claude Opus 4.7 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index74
| Benchmark | Claude Opus 4.7 | Kimi K3 | Leader |
|---|---|---|---|
| MMLU Pro | 89.9% | 88.0% | Claude Opus 4.7 |
| LegalBench (Vals AI) | 85.3% | 86.2% | Kimi K3 |
| CaseLaw (Vals AI) | 68.4% | Not measured | Only Claude Opus 4.7 measured |
| CorpFin (Vals AI) | 66.1% | 71.6% | Kimi K3 |
| TaxEval (Vals AI) | 75.3% | 75.7% | Kimi K3 |
| MortgageTax (Vals AI) | 70.3% | 66.3% | Claude Opus 4.7 |
| MedCode (Vals AI) | 54.9% | 49.4% | Claude Opus 4.7 |
| SimpleQA Verified | 51.7% | 50.6% | Claude Opus 4.7 |
| LMArena Text: science | 1508 | 1508 | Kimi K3 |
| LMArena Text: medicine and healthcare | 1495 | 1489 | Claude Opus 4.7 |
| LMArena Text: legal and government | 1504 | 1503 | Claude Opus 4.7 |
| LMArena Text: business and finance | 1490 | 1470 | Claude Opus 4.7 |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Claude Opus 4.7 | Kimi K3 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1336 | Only Kimi K3 measured |
| Design Arena: UI components | Not measured | 1345 | Only Kimi K3 measured |
| Design Arena: game dev | Not measured | 1361 | Only Kimi K3 measured |
| Design Arena: data viz | Not measured | 1350 | Only Kimi K3 measured |
| Design Arena: 3D | Not measured | 1388 | Only Kimi K3 measured |
| Design Arena: all code categories | Not measured | 1361 | Only Kimi K3 measured |
| Design Arena: SVG | Not measured | 1301 | Only Kimi K3 measured |
| LiveBench design | Not measured | 77.2% | Only Kimi K3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index186
| Benchmark | Claude Opus 4.7 | Kimi K3 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 53.0% | Only Kimi K3 measured |
| LiveBench data analysis | Not measured | 78.7% | Only Kimi K3 measured |
| Public Benefits Bench (Vals AI) | Not measured | 68.2% | Only Kimi K3 measured |
| SAGE (Vals AI) | 56.1% | 52.8% | Claude Opus 4.7 |
| MedScribe (Vals AI) | 83.0% | 88.0% | Kimi K3 |
| Vals Multimodal Index | 67.4% | 73.4% | Kimi K3 |
| IFBench | 58.6% | Not measured | Only Claude Opus 4.7 measured |
| Long context reasoning (AA-LCR) | 78.7% | 88.7% | Kimi K3 |
| DTBench | 94.7% | 91.2% | Claude Opus 4.7 |
| LMCA | 52.2% | 52.7% | Kimi K3 |
| Surface Evolver Bench | Not measured | 95.0% | Only Kimi K3 measured |
| Furniture assembly | 33.3% | 34.2% | Kimi K3 |
| ExploitBench | 26.5% | Not measured | Only Claude Opus 4.7 measured |
| LMArena Text | 1490 | 1476 | Claude Opus 4.7 |
| LMArena Text: instruction following | 1498 | 1485 | Claude Opus 4.7 |
| LMArena Text: creative writing | 1486 | 1457 | Claude Opus 4.7 |
| LMArena Vision | 1317 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Text: English | 1496 | 1481 | Claude Opus 4.7 |
| LMArena Text: non-English | 1480 | 1466 | Claude Opus 4.7 |
| LMArena Text: Chinese | 1531 | 1529 | Claude Opus 4.7 |
| LMArena Text: German | 1495 | 1490 | Claude Opus 4.7 |
| LMArena Text: Japanese | 1474 | 1494 | Kimi K3 |
| LMArena Text: Korean | 1464 | 1460 | Claude Opus 4.7 |
| LMArena Text: French | 1503 | 1492 | Claude Opus 4.7 |
| LMArena Text: Spanish | 1494 | 1472 | Claude Opus 4.7 |
| LMArena Text: Russian | 1494 | 1485 | Claude Opus 4.7 |
| LMArena Text: Polish | 1489 | 1458 | Claude Opus 4.7 |
| LMArena Text: multi-turn | 1505 | 1489 | Claude Opus 4.7 |
| LMArena Text: longer queries | 1505 | 1494 | Claude Opus 4.7 |
| LMArena Text: writing and language | 1492 | 1471 | Claude Opus 4.7 |
| LMArena Text: entertainment and media | 1474 | 1453 | Claude Opus 4.7 |
| LMArena Vision: English | 1322 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: Chinese | 1371 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: reading text | 1327 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: humor | 1309 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: recognizing things | 1278 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Vision: creative writing | 1326 | Not measured | Only Claude Opus 4.7 measured |
| LMArena Document | 1495 | Not measured | Only Claude Opus 4.7 measured |
| 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
| Benchmark | Claude Opus 4.7 | Kimi K3 | 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 K3 costs less
Repository review
50K input + 3K output tokens
Kimi K3 costs less
Agent loop
200K input + 10K output tokens
Kimi K3 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 4.7 | MoonshotAI Kimi K3 |
|---|---|---|
| Maker | Anthropic | Moonshot AI |
| Weights | No public weights listed | Open weights |
| Released | April 16, 2026 | July 16, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $5.00 | $0.239 |
| Output $/Mtok | $25.00 | $11.936 |
| Coding index | 51.1 | 61.8 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $2.95 | $0.81 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.7 better than Kimi K3 for coding?
Pick Kimi K3 for coding: it scores 61.8 on the Vibe Coding Index against 51.1 for Claude Opus 4.7. Pick Claude Opus 4.7 when what matters is Code migration (Vals AI) or LMArena Text: coding, where it leads.
Which is cheaper, Claude Opus 4.7 or Kimi K3?
Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; Kimi K3 costs $0.239 and $11.936. Per solved SWE-bench Verified task, Claude Opus 4.7 costs $2.95 and Kimi K3 $0.81.
Which has the bigger context window, Claude Opus 4.7 or Kimi K3?
Kimi K3, with 1.05M tokens against 1M.
How many benchmarks is the Claude Opus 4.7 vs Kimi K3 comparison based on?
79 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.7's coding index rests on 1 independent benchmark and Kimi K3's on 2. Where only one model has a result, the page says so instead of naming a winner.