Kimi K3 vs Inkling Small
Updated October 21, 2026. 75 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 29.9 for Inkling Small.
Pick Inkling Small when output tokens cost 9.9x less, or when a solved task costs $0.16 against $0.81.
- Shared results
- 75
- Kimi K3 only
- 42
- Inkling Small only
- 9
- 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 29.9.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Kimi K3
Kimi K3 leads, 43.6 against 25.7.
Same board, both measured
Agentic work
AA Agentic Index
Kimi K3
Kimi K3 leads, 50.0 against 23.5.
Same board, both measured
Reasoning
GPQA Diamond
Kimi K3
Kimi K3 leads, 92.9% against 83.6%.
Same board, both measured
Knowledge
MMLU Pro
Kimi K3
Kimi K3 leads, 88.0% against 85.6%.
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
Kimi K3
Kimi K3 leads, 53.0% against 27.6%.
Same board, both measured
Long documents
Listed context window
Kimi K3
Kimi K3 takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling Small
Kimi K3 $0.0062, Inkling Small $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Inkling Small
Kimi K3 $0.81, Inkling Small $0.16.
Published attempt cost and pass rate
At a glance
- Coding index
- Kimi K3 61.8 from 2 benchmarks, Inkling Small 29.9 from 1 benchmark.
- Widest category
- Math, 25.4 points apart on average over 6 shared benchmarks.
- Widest single gap
- ProofBench: Kimi K3 87.0% against Inkling Small 6.0%, 81.0 points apart on a 0 to 100 scale.
- Output price
- Kimi K3 $11.936 against Inkling Small $1.20 per million output tokens, 9.9x apart.
- Context window
- Kimi K3 takes 1.05M tokens, Inkling Small 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 K3 | Bars | Inkling Small | Ties |
|---|---|---|---|---|
| Coding | 17 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 6 | 0 | ||
| Reasoning | 10 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 11 | 0 | ||
| General | 23 | 0 | ||
| All shared boards | 75 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index170
| Benchmark | Kimi K3 | Inkling Small | Leader |
|---|---|---|---|
| LiveBench coding | 59.3% | Not measured | Only Kimi K3 measured |
| LMArena WebDev | 1655 | 1409 | Kimi K3 |
| AA Coding Index | 76.2 | 52.9 | Kimi K3 |
| LiveCodeBench (Vals AI) | 87.2% | 85.9% | Kimi K3 |
| SWE-bench Verified (Vals AI) | 93.4% | 82.2% | Kimi K3 |
| Terminal-Bench 4 (Vals AI) | 17.2% | 0.0% | Kimi K3 |
| Vibe Code Bench (Vals AI) | 85.0% | 19.1% | Kimi K3 |
| Code migration (Vals AI) | 16.1% | 13.7% | Kimi K3 |
| ProgramBench (Vals AI) | 2.0% | 0.5% | Kimi K3 |
| IOI (Vals AI) | 48.9% | 9.3% | Kimi K3 |
| Terminal-Bench 2.1 (Vals AI) | 80.9% | 55.1% | Kimi K3 |
| SWE-bench Multimodal (Vals AI) | 44.2% | Not measured | Only Kimi K3 measured |
| Vibe Code Bench 1-100 (Vals AI) | 18.2% | Not measured | Only Kimi K3 measured |
| SkillsBench (Vals AI) | Not measured | 33.6% | Only Inkling Small measured |
| CyberBench (Vals AI) | 75.2% | 64.1% | Kimi K3 |
| SciCode | 59.5% | 49.7% | Kimi K3 |
| FrontierCode | 44.2% | Not measured | Only Kimi K3 measured |
| FrontierSWE | 25.9% | Not measured | Only Kimi K3 measured |
| WeirdML | 82.6% | Not measured | Only Kimi K3 measured |
| ALE-Bench | 1524.5 | Not measured | Only Kimi K3 measured |
| LMArena Text: coding | 1508 | 1450 | Kimi K3 |
| LMArena Text: software and IT | 1499 | 1447 | Kimi K3 |
| LMArena WebDev: React | 1670 | 1399 | Kimi K3 |
| LMArena WebDev: HTML | 1644 | 1398 | Kimi K3 |
| LMArena WebDev: from an image | 1579 | 1410 | Kimi K3 |
| Neither model has a result on the other 13 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K3 | Inkling Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.6 | 25.7 | Kimi K3 |
| Epoch Capabilities Index | 157.9 | 150.3 | Kimi K3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Kimi K3 | Inkling Small | Leader |
|---|---|---|---|
| AA Agentic Index | 50.0 | 23.5 | Kimi K3 |
| Design Arena: agents building web apps | 1296 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building full-stack apps | 1315 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building mobile apps | 1267 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building Android apps | 1256 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building Godot games | 1223 | Not measured | Only Kimi K3 measured |
| Design Arena: agents building games | 1252 | Not measured | Only Kimi K3 measured |
| Design Arena: HTML slides | 1256 | Not measured | Only Kimi K3 measured |
| Design Arena: PowerPoint slides | 1273 | Not measured | Only Kimi K3 measured |
| Design Arena: spreadsheets | 1058 | Not measured | Only Kimi K3 measured |
| LiveBench research | 79.0% | Not measured | Only Kimi K3 measured |
| LiveBench browser | 16.0% | Not measured | Only Kimi K3 measured |
| LiveBench long agentic | 42.8% | Not measured | Only Kimi K3 measured |
| Finance Agent (Vals AI) | 53.1% | 41.3% | Kimi K3 |
| Tax Agent Bench (Vals AI) | 33.4% | 15.4% | Kimi K3 |
| Legal Research Bench (Vals AI) | 46.1% | 25.5% | Kimi K3 |
| Harvey's Legal Agent Benchmark (Vals AI) | 12.9% | 2.9% | Kimi K3 |
| Excel Modeling Benchmark (Vals AI) | 66.7% | 31.8% | Kimi K3 |
| BioMysteryBench (Vals AI) | 72.6% | Not measured | Only Kimi K3 measured |
| Terminal-Bench-Science (Vals AI) | 1.4% | Not measured | Only Kimi K3 measured |
| Time Horizon Index (Vals AI) | 10.5% | Not measured | Only Kimi K3 measured |
| APEX-Agents | 47.8% | Not measured | Only Kimi K3 measured |
| PostTrainBench | 32.0% | Not measured | Only Kimi K3 measured |
| Vending-Bench 2 | $5,165 | Not measured | Only Kimi K3 measured |
| Neither model has a result on the other 15 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
| Benchmark | Kimi K3 | Inkling Small | Leader |
|---|---|---|---|
| GPQA Diamond | 92.9% | 83.6% | Kimi K3 |
| LiveBench reasoning | 90.7% | Not measured | Only Kimi K3 measured |
| MMMU Pro (Vals AI) | 88.2% | Not measured | Only Kimi K3 measured |
| GPQA Diamond (Artificial Analysis run) | 93.5% | 89.5% | Kimi K3 |
| Humanity's Last Exam (Artificial Analysis run) | 46.9% | 33.3% | Kimi K3 |
| GPQA Diamond (Epoch AI run) | 93.1% | 88.5% | Kimi K3 |
| ARC-AGI | 94.5% | 84.0% | Kimi K3 |
| ARC-AGI-2 | 60.4% | 40.1% | Kimi K3 |
| SimpleBench | 60.7% | Not measured | Only Kimi K3 measured |
| Chess puzzles | 37.0% | Not measured | Only Kimi K3 measured |
| Mystery game puzzles | 26.0% | 6.0% | Kimi K3 |
| LMArena Text: hard prompts | 1495 | 1423 | Kimi K3 |
| LMArena Text: expert | 1520 | 1441 | Kimi K3 |
| LMArena Text: hard prompts in English | 1496 | 1429 | Kimi K3 |
| LMArena Vision: diagrams | Not measured | 1251 | Only Inkling Small measured |
| LMArena Vision: homework | Not measured | 1257 | Only Inkling Small measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Kimi K3 | Inkling Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 97.2% | 90.0% | Kimi K3 |
| FrontierMath, tiers 1 to 3 | 72.2% | 46.3% | Kimi K3 |
| FrontierMath, tier 4 | 39.0% | 17.1% | Kimi K3 |
| ProofBench | 87.0% | 6.0% | Kimi K3 |
| LMArena Text: math | 1494 | 1459 | Kimi K3 |
| LMArena Text: mathematical work | 1505 | 1441 | Kimi K3 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Kimi K3 | Inkling Small | Leader |
|---|---|---|---|
| MMLU Pro | 88.0% | 85.6% | Kimi K3 |
| LegalBench (Vals AI) | 86.2% | 83.0% | Kimi K3 |
| CorpFin (Vals AI) | 71.6% | 69.6% | Kimi K3 |
| TaxEval (Vals AI) | 75.7% | 75.5% | Kimi K3 |
| MortgageTax (Vals AI) | 66.3% | 62.3% | Kimi K3 |
| MedCode (Vals AI) | 49.4% | 37.9% | Kimi K3 |
| SimpleQA Verified | 50.6% | 19.1% | Kimi K3 |
| LMArena Text: science | 1508 | 1428 | Kimi K3 |
| LMArena Text: medicine and healthcare | 1489 | 1413 | Kimi K3 |
| LMArena Text: legal and government | 1503 | 1415 | Kimi K3 |
| LMArena Text: business and finance | 1470 | 1413 | Kimi K3 |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Kimi K3 | Inkling Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1336 | Not measured | Only Kimi K3 measured |
| Design Arena: UI components | 1345 | Not measured | Only Kimi K3 measured |
| Design Arena: game dev | 1361 | Not measured | Only Kimi K3 measured |
| Design Arena: data viz | 1350 | Not measured | Only Kimi K3 measured |
| Design Arena: 3D | 1388 | Not measured | Only Kimi K3 measured |
| Design Arena: all code categories | 1361 | Not measured | Only Kimi K3 measured |
| Design Arena: SVG | 1301 | Not measured | Only Kimi K3 measured |
| LiveBench design | 77.2% | Not measured | 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 index230
| Benchmark | Kimi K3 | Inkling Small | Leader |
|---|---|---|---|
| Vals Index | 53.0% | 27.6% | Kimi K3 |
| LiveBench data analysis | 78.7% | Not measured | Only Kimi K3 measured |
| Public Benefits Bench (Vals AI) | 68.2% | 59.4% | Kimi K3 |
| SAGE (Vals AI) | 52.8% | 32.7% | Kimi K3 |
| MedScribe (Vals AI) | 88.0% | 84.1% | Kimi K3 |
| Vals Multimodal Index | 73.4% | 50.0% | Kimi K3 |
| Long context reasoning (AA-LCR) | 88.7% | 75.7% | Kimi K3 |
| DTBench | 91.2% | Not measured | Only Kimi K3 measured |
| LMCA | 52.7% | Not measured | Only Kimi K3 measured |
| Surface Evolver Bench | 95.0% | Not measured | Only Kimi K3 measured |
| Furniture assembly | 34.2% | Not measured | Only Kimi K3 measured |
| LMArena Text | 1476 | 1413 | Kimi K3 |
| LMArena Text: instruction following | 1485 | 1399 | Kimi K3 |
| LMArena Text: creative writing | 1457 | 1334 | Kimi K3 |
| LMArena Vision | Not measured | 1237 | Only Inkling Small measured |
| LMArena Text: English | 1481 | 1421 | Kimi K3 |
| LMArena Text: non-English | 1466 | 1401 | Kimi K3 |
| LMArena Text: Chinese | 1529 | 1464 | Kimi K3 |
| LMArena Text: German | 1490 | 1408 | Kimi K3 |
| LMArena Text: Japanese | 1494 | 1401 | Kimi K3 |
| LMArena Text: Korean | 1460 | 1367 | Kimi K3 |
| LMArena Text: French | 1492 | 1435 | Kimi K3 |
| LMArena Text: Spanish | 1472 | 1422 | Kimi K3 |
| LMArena Text: Russian | 1485 | 1394 | Kimi K3 |
| LMArena Text: Polish | 1458 | 1428 | Kimi K3 |
| LMArena Text: multi-turn | 1489 | 1416 | Kimi K3 |
| LMArena Text: longer queries | 1494 | 1402 | Kimi K3 |
| LMArena Text: writing and language | 1471 | 1357 | Kimi K3 |
| LMArena Text: entertainment and media | 1453 | 1352 | Kimi K3 |
| LMArena Vision: English | Not measured | 1243 | Only Inkling Small measured |
| LMArena Vision: Chinese | Not measured | 1292 | Only Inkling Small measured |
| LMArena Vision: reading text | Not measured | 1243 | Only Inkling Small measured |
| LMArena Vision: humor | Not measured | 1207 | Only Inkling Small measured |
| LMArena Vision: creative writing | Not measured | 1205 | Only Inkling Small measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K3 | Inkling Small | 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
Inkling Small costs less
Repository review
50K input + 3K output tokens
Inkling Small costs less
Agent loop
200K input + 10K output tokens
Inkling Small 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 K3 | Thinking Machines Inkling Small |
|---|---|---|
| Maker | Moonshot AI | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | July 16, 2026 | July 30, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $0.239 | $0.45 |
| Output $/Mtok | $11.936 | $1.20 |
| Coding index | 61.8 | 29.9 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $0.81 | $0.16 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K3 better than Inkling Small for coding?
Pick Kimi K3 for coding: it scores 61.8 on the Vibe Coding Index against 29.9 for Inkling Small. Pick Inkling Small when output tokens cost 9.9x less, or when a solved task costs $0.16 against $0.81.
Which is cheaper, Kimi K3 or Inkling Small?
Kimi K3 costs $0.239 per million input tokens and $11.936 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, Kimi K3 costs $0.81 and Inkling Small $0.16.
Which has the bigger context window, Kimi K3 or Inkling Small?
Kimi K3, with 1.05M tokens against 524K.
How many benchmarks is the Kimi K3 vs Inkling Small comparison based on?
75 benchmarks have a result for both models as of October 21, 2026. Kimi K3's coding index rests on 2 independent benchmarks and Inkling Small's on 1. Where only one model has a result, the page says so instead of naming a winner.