Kimi K3.1 Pro vs Inkling 2 Small
Kimi K3.1 Pro leads Inkling 2 Small on coding, 79.0 to 48.9 on the Vibe Coding Index, and Inkling 2 Small costs 10.0x less per output token ($1.00 vs $10.00 per million). Updated November 14, 2026; 43 benchmarks have a result for both.
Kimi K3.1 Pro or Inkling 2 Small: which to pick
Pick Kimi K3.1 Pro for coding: it scores 79.0 on the Vibe Coding Index against 48.9 for Inkling 2 Small.
Pick Inkling 2 Small for output tokens 10.0x cheaper ($1.00 vs $10.00 per million) and work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
- Shared results
- 43
- Kimi K3.1 Pro only
- 36
- Inkling 2 Small only
- 8
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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, six public coding benchmarks
Kimi K3.1 Pro
Kimi K3.1 Pro scores 79.0 against 48.9.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Kimi K3.1 Pro
Kimi K3.1 Pro leads, 46.5 against 30.6.
Same board, both measured
Web design
Design Arena: websites
No call
Only Kimi K3.1 Pro has a Design Arena: websites result, 1321.
Directional only
General
Vals Index
Kimi K3.1 Pro
Kimi K3.1 Pro leads, 62.5% against 56.1%.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Small
Kimi K3.1 Pro $0.0070, Inkling 2 Small $0.0008 per turn.
List prices
At a glance
- Coding index
- Kimi K3.1 Pro 79.0 from 4 benchmarks, Inkling 2 Small 48.9 from 3 benchmarks.
- Widest category
- Intelligence, 15.9 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench 4 (Vals AI): Kimi K3.1 Pro 63.6% against Inkling 2 Small 12.6%, 68.0 points apart on a 0 to 100 scale.
- Output price
- Kimi K3.1 Pro $10.00 against Inkling 2 Small $1.00 per million output tokens, 10.0x apart.
- Context window
- Both take 1.05M tokens.
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 K3.1 Pro | Bars | Inkling 2 Small | Ties |
|---|---|---|---|---|
| Coding | 10 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 5 | 3 | ||
| Reasoning | 7 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 3 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 40 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index100
| Benchmark | Kimi K3.1 Pro | Inkling 2 Small | Leader |
|---|---|---|---|
| LiveBench coding | 67.8% | Not measured | Only Kimi K3.1 Pro measured |
| LMArena WebDev | 1687 | 1647 | Kimi K3.1 Pro |
| Terminal-Bench 4 (Vals AI) | 63.6% | 12.6% | Kimi K3.1 Pro |
| Vibe Code Bench (Vals AI) | 84.9% | 81.5% | Kimi K3.1 Pro |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only Inkling 2 Small measured |
| IOI (Vals AI) | 81.9% | Not measured | Only Kimi K3.1 Pro measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 43.1% | Only Inkling 2 Small measured |
| CyberBench (Vals AI) | Not measured | 72.7% | Only Inkling 2 Small measured |
| SciCode | 60.8% | 52.3% | Kimi K3.1 Pro |
| Terminal-Bench 4.0 (Artificial Analysis run) | 67.2% | 13.1% | Kimi K3.1 Pro |
| FrontierCode 2.0 | 25.5% | 25.4% | Kimi K3.1 Pro |
| ALE-Bench | 1932.8 | Not measured | Only Kimi K3.1 Pro measured |
| LMArena Text: coding | 1480 | 1455 | Kimi K3.1 Pro |
| LMArena Text: software and IT | 1482 | 1443 | Kimi K3.1 Pro |
| LMArena WebDev: React | 1699 | 1660 | Kimi K3.1 Pro |
| LMArena WebDev: HTML | 1689 | 1661 | Kimi K3.1 Pro |
| SWE-Bench Pro V2 | Not measured | 97.7% | Only Inkling 2 Small measured |
| GameBench 2 | 84.0 | Not measured | Only Kimi K3.1 Pro measured |
| Terminal-Bench 4.0 | 60.9% | Not measured | Only Kimi K3.1 Pro measured |
| Neither model has a result on the other 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K3.1 Pro | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 46.5 | 30.6 | Kimi K3.1 Pro |
| Epoch Capabilities Index | 161.4 | Not measured | Only Kimi K3.1 Pro measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index53
| Benchmark | Kimi K3.1 Pro | Inkling 2 Small | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1312 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: agents building full-stack apps | 1321 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: agents building mobile apps | 1268 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: agents building Android apps | 1147 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: PowerPoint slides | 1278 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: spreadsheets | 1326 | Not measured | Only Kimi K3.1 Pro measured |
| LiveBench research | 82.1% | Not measured | Only Kimi K3.1 Pro measured |
| LiveBench browser | 75.9% | Not measured | Only Kimi K3.1 Pro measured |
| LiveBench long agentic | 38.7% | Not measured | Only Kimi K3.1 Pro measured |
| SREBench (Vals AI) | 27.1% | 1.9% | Kimi K3.1 Pro |
| Tax Agent Bench (Vals AI) | 24.9% | 38.9% | Inkling 2 Small |
| Legal Research Bench (Vals AI) | 37.5% | 46.6% | Inkling 2 Small |
| Harvey's Legal Agent Benchmark (Vals AI) | 11.7% | 21.7% | Inkling 2 Small |
| BioMysteryBench (Vals AI) | 75.6% | 70.0% | Kimi K3.1 Pro |
| Terminal-Bench-Science (Vals AI) | 31.4% | 2.9% | Kimi K3.1 Pro |
| Vals Science Index | 44.4% | 32.7% | Kimi K3.1 Pro |
| APEX-Agents | 65.5% | 46.8% | Kimi K3.1 Pro |
| MCP Atlas | Not measured | 85.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 26 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Kimi K3.1 Pro | Inkling 2 Small | Leader |
|---|---|---|---|
| LiveBench reasoning | 91.1% | Not measured | Only Kimi K3.1 Pro measured |
| MysteryMechanism (Vals AI) | 26.1% | 25.2% | Kimi K3.1 Pro |
| Humanity's Last Exam (Artificial Analysis run) | 52.5% | 44.1% | Kimi K3.1 Pro |
| HLE-Diamond (Artificial Analysis run) | 37.3% | 28.7% | Kimi K3.1 Pro |
| CritPt v2, hard subset (Artificial Analysis run) | 49.5% | 35.0% | Kimi K3.1 Pro |
| ARC-AGI | Not measured | 96.5% | Only Inkling 2 Small measured |
| ARC-AGI-2 | Not measured | 81.7% | Only Inkling 2 Small measured |
| LMArena Text: hard prompts | 1471 | 1421 | Kimi K3.1 Pro |
| LMArena Text: expert | 1489 | 1478 | Kimi K3.1 Pro |
| LMArena Text: hard prompts in English | 1486 | 1424 | Kimi K3.1 Pro |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K3.1 Pro | Inkling 2 Small | Leader |
|---|---|---|---|
| ProofBench | 91.0% | Not measured | Only Kimi K3.1 Pro measured |
| LMArena Text: mathematical work | 1451 | Not measured | Only Kimi K3.1 Pro measured |
| MathArena | 54.3% | 42.4% | Kimi K3.1 Pro |
| Neither model has a result on the other 11 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Kimi K3.1 Pro | Inkling 2 Small | Leader |
|---|---|---|---|
| AA-Omniscience | 29.9 | 16.1 | Kimi K3.1 Pro |
| LMArena Text: science | 1464 | 1409 | Kimi K3.1 Pro |
| LMArena Text: medicine and healthcare | 1413 | Not measured | Only Kimi K3.1 Pro measured |
| LMArena Text: legal and government | 1495 | Not measured | Only Kimi K3.1 Pro measured |
| LMArena Text: business and finance | 1472 | 1415 | Kimi K3.1 Pro |
| PRBench Finance | 47.5% | Not measured | Only Kimi K3.1 Pro measured |
| PRBench Legal | 47.9% | Not measured | Only Kimi K3.1 Pro measured |
| Neither model has a result on the other 14 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Kimi K3.1 Pro | Inkling 2 Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1321 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: UI components | 1389 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: game dev | 1404 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: data viz | 1298 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: 3D | 1442 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: all code categories | 1350 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: SVG | 1329 | Not measured | Only Kimi K3.1 Pro measured |
| Design Arena: ASCII art | 1301 | Not measured | Only Kimi K3.1 Pro measured |
| LiveBench design | 73.7% | Not measured | Only Kimi K3.1 Pro measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Kimi K3.1 Pro | Inkling 2 Small | Leader |
|---|---|---|---|
| Vals Index | 62.5% | 56.1% | Kimi K3.1 Pro |
| LiveBench data analysis | 79.1% | Not measured | Only Kimi K3.1 Pro measured |
| SAGE (Vals AI) | Not measured | 88.6% | Only Inkling 2 Small measured |
| Long context reasoning (AA-LCR) | 86.3% | 83.3% | Kimi K3.1 Pro |
| GDPval-AA | 1861 | 1630 | Kimi K3.1 Pro |
| DTBench | 93.3% | Not measured | Only Kimi K3.1 Pro measured |
| LMCA | 57.6% | Not measured | Only Kimi K3.1 Pro measured |
| LMArena Text | 1459 | 1403 | Kimi K3.1 Pro |
| LMArena Text: instruction following | 1472 | 1408 | Kimi K3.1 Pro |
| LMArena Text: creative writing | 1439 | 1348 | Kimi K3.1 Pro |
| LMArena Text: English | 1466 | 1418 | Kimi K3.1 Pro |
| LMArena Text: non-English | 1450 | 1390 | Kimi K3.1 Pro |
| LMArena Text: Chinese | 1516 | Not measured | Only Kimi K3.1 Pro measured |
| LMArena Text: Spanish | 1503 | Not measured | Only Kimi K3.1 Pro measured |
| LMArena Text: Russian | 1452 | 1377 | Kimi K3.1 Pro |
| LMArena Text: multi-turn | 1449 | 1408 | Kimi K3.1 Pro |
| LMArena Text: longer queries | 1468 | 1403 | Kimi K3.1 Pro |
| LMArena Text: writing and language | 1458 | 1381 | Kimi K3.1 Pro |
| LMArena Text: entertainment and media | 1460 | 1359 | Kimi K3.1 Pro |
| Neither model has a result on the other 30 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K3.1 Pro | Inkling 2 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 2 Small costs less
Repository review
50K input + 3K output tokens
Inkling 2 Small costs less
Agent loop
200K input + 10K output tokens
Inkling 2 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 K3.1 Pro | Thinking Machines Inkling 2 Small |
|---|---|---|
| Maker | Moonshot AI | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | October 23, 2026 | November 9, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $2.00 | $0.30 |
| Output $/Mtok | $10.00 | $1.00 |
| Coding index | 79.0 | 48.9 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K3.1 Pro better than Inkling 2 Small for coding?
Pick Kimi K3.1 Pro for coding: it scores 79.0 on the Vibe Coding Index against 48.9 for Inkling 2 Small. Pick Inkling 2 Small for output tokens 10.0x cheaper ($1.00 vs $10.00 per million) and work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
Which is cheaper, Kimi K3.1 Pro or Inkling 2 Small?
Kimi K3.1 Pro costs $2.00 per million input tokens and $10.00 per million output tokens; Inkling 2 Small costs $0.30 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Kimi K3.1 Pro or Inkling 2 Small?
Neither: both take 1.05M tokens.
How many benchmarks is the Kimi K3.1 Pro vs Inkling 2 Small comparison based on?
43 benchmarks have a result for both models as of November 14, 2026. Kimi K3.1 Pro's coding index rests on 4 independent benchmarks and Inkling 2 Small's on 3. Where only one model has a result, the page says so instead of naming a winner.