Inkling 2 Small vs Inkling Small
Inkling 2 Small leads Inkling Small on coding, 48.9 to 27.3 on the Vibe Coding Index, and Inkling 2 Small costs 1.2x less per output token ($1.00 vs $1.20 per million). Updated November 14, 2026; 41 benchmarks have a result for both.
Inkling 2 Small or Inkling Small: which to pick
Pick Inkling 2 Small for coding: it scores 48.9 on the Vibe Coding Index against 27.3 for Inkling Small, though on 3 benchmarks against 4.
Pick Inkling Small for work measured by LMArena Text: software and IT or LMArena Text: hard prompts, where it leads.
- Shared results
- 41
- Inkling 2 Small only
- 10
- Inkling Small only
- 52
- Like-for-like categories
- 6 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
Inkling 2 Small
Inkling 2 Small scores 48.9 against 27.3.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Inkling 2 Small
Inkling 2 Small leads, 30.6 against 12.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Inkling Small has a AA Agentic Index result, 23.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Inkling Small has a GPQA Diamond result, 83.6%.
Directional only
Knowledge
MMLU Pro
No call
Only Inkling Small has a MMLU Pro result, 85.6%.
Directional only
General
Vals Index
Inkling 2 Small
Inkling 2 Small leads, 56.1% against 27.6%.
Same board, both measured
Long documents
Listed context window
Inkling 2 Small
Inkling 2 Small takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Small
Inkling 2 Small $0.0008, Inkling Small $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Inkling Small has the number, $0.16.
Directional only
At a glance
- Coding index
- Inkling 2 Small 48.9 from 3 benchmarks, Inkling Small 27.3 from 4 benchmarks.
- Widest category
- Coding, 18.9 points apart on average over 12 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Inkling 2 Small 81.5% against Inkling Small 19.1%, 62.5 points apart on a 0 to 100 scale.
- Output price
- Inkling 2 Small $1.00 against Inkling Small $1.20 per million output tokens, 1.2x apart.
- Context window
- Inkling 2 Small 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 | Inkling 2 Small | Bars | Inkling Small | Ties |
|---|---|---|---|---|
| Coding | 10 | 1 | 1 tie | |
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 0 | ||
| Reasoning | 6 | 2 | ||
| Knowledge | 2 | 1 | ||
| General | 7 | 6 | ||
| All shared boards | 30 | 10 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index101
| Benchmark | Inkling 2 Small | Inkling Small | Leader |
|---|---|---|---|
| LMArena WebDev | 1647 | 1408 | Inkling 2 Small |
| AA Coding Index | Not measured | 52.9 | Only Inkling Small measured |
| LiveCodeBench (Vals AI) | Not measured | 85.9% | Only Inkling Small measured |
| SWE-bench Verified (Vals AI) | Not measured | 82.2% | Only Inkling Small measured |
| Terminal-Bench 4 (Vals AI) | 12.6% | 0.0% | Inkling 2 Small |
| Vibe Code Bench (Vals AI) | 81.5% | 19.1% | Inkling 2 Small |
| Code migration (Vals AI) | Not measured | 13.7% | Only Inkling Small measured |
| ProgramBench (Vals AI) | 0.5% | 0.5% | Tie |
| IOI (Vals AI) | Not measured | 9.3% | Only Inkling Small measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 55.1% | Only Inkling Small measured |
| SWE-bench Multimodal (Vals AI) | 43.1% | Not measured | Only Inkling 2 Small measured |
| SkillsBench (Vals AI) | Not measured | 33.6% | Only Inkling Small measured |
| CyberBench (Vals AI) | 72.7% | 64.1% | Inkling 2 Small |
| SciCode | 52.3% | 49.7% | Inkling 2 Small |
| Terminal-Bench 4.0 (Artificial Analysis run) | 13.1% | 1.0% | Inkling 2 Small |
| FrontierCode 2.0 | 25.4% | 4.8% | Inkling 2 Small |
| LMArena Text: coding | 1455 | 1451 | Inkling 2 Small |
| LMArena Text: software and IT | 1443 | 1448 | Inkling Small |
| LMArena WebDev: React | 1660 | 1397 | Inkling 2 Small |
| LMArena WebDev: HTML | 1661 | 1396 | Inkling 2 Small |
| LMArena WebDev: from an image | Not measured | 1410 | Only Inkling Small measured |
| SWE-Bench Pro V2 | 97.7% | Not measured | Only Inkling 2 Small measured |
| GameBench 2 | Not measured | 33.1 | Only Inkling Small measured |
| Terminal-Bench 4.0 | Not measured | 0.9% | Only Inkling Small measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Inkling 2 Small | Inkling Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.6 | 12.9 | Inkling 2 Small |
| Epoch Capabilities Index | Not measured | 150.8 | Only Inkling Small measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Inkling 2 Small | Inkling Small | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 23.5 | Only Inkling Small measured |
| SREBench (Vals AI) | 1.9% | Not measured | Only Inkling 2 Small measured |
| Finance Agent (Vals AI) | Not measured | 41.3% | Only Inkling Small measured |
| Tax Agent Bench (Vals AI) | 38.9% | 15.4% | Inkling 2 Small |
| Legal Research Bench (Vals AI) | 46.6% | 25.5% | Inkling 2 Small |
| Harvey's Legal Agent Benchmark (Vals AI) | 21.7% | 2.9% | Inkling 2 Small |
| Excel Modeling Benchmark (Vals AI) | Not measured | 31.8% | Only Inkling Small measured |
| BioMysteryBench (Vals AI) | 70.0% | Not measured | Only Inkling 2 Small measured |
| Terminal-Bench-Science (Vals AI) | 2.9% | Not measured | Only Inkling 2 Small measured |
| Vals Science Index | 32.7% | Not measured | Only Inkling 2 Small measured |
| APEX-Agents | 46.8% | Not measured | Only Inkling 2 Small measured |
| MCP Atlas | 85.4% | 79.2% | Inkling 2 Small |
| Toolathlon-Verified | Not measured | 54.4% | Only Inkling Small measured |
| Neither model has a result on the other 31 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | Inkling 2 Small | Inkling Small | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 83.6% | Only Inkling Small measured |
| MysteryMechanism (Vals AI) | 25.2% | Not measured | Only Inkling 2 Small measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.5% | Only Inkling Small measured |
| Humanity's Last Exam (Artificial Analysis run) | 44.1% | 33.3% | Inkling 2 Small |
| HLE-Diamond (Artificial Analysis run) | 28.7% | 12.1% | Inkling 2 Small |
| CritPt v2, hard subset (Artificial Analysis run) | 35.0% | 18.5% | Inkling 2 Small |
| GPQA Diamond (Epoch AI run) | Not measured | 88.5% | Only Inkling Small measured |
| ARC-AGI | 96.5% | 84.0% | Inkling 2 Small |
| ARC-AGI-2 | 81.7% | 40.1% | Inkling 2 Small |
| Mystery game puzzles | Not measured | 6.0% | Only Inkling Small measured |
| LMArena Text: hard prompts | 1421 | 1425 | Inkling Small |
| LMArena Text: expert | 1478 | 1440 | Inkling 2 Small |
| LMArena Text: hard prompts in English | 1424 | 1429 | Inkling Small |
| LMArena Vision: diagrams | Not measured | 1253 | Only Inkling Small measured |
| LMArena Vision: homework | Not measured | 1252 | Only Inkling Small measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Inkling 2 Small | Inkling Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 90.0% | Only Inkling Small measured |
| FrontierMath, tiers 1 to 3 | Not measured | 46.3% | Only Inkling Small measured |
| FrontierMath, tier 4 | Not measured | 17.1% | Only Inkling Small measured |
| ProofBench | Not measured | 6.0% | Only Inkling Small measured |
| LMArena Text: math | Not measured | 1459 | Only Inkling Small measured |
| LMArena Text: mathematical work | Not measured | 1437 | Only Inkling Small measured |
| MathArena | 42.4% | Not measured | Only Inkling 2 Small measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Inkling 2 Small | Inkling Small | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 85.6% | Only Inkling Small measured |
| LegalBench (Vals AI) | Not measured | 83.0% | Only Inkling Small measured |
| CorpFin (Vals AI) | Not measured | 69.6% | Only Inkling Small measured |
| TaxEval (Vals AI) | Not measured | 75.5% | Only Inkling Small measured |
| MortgageTax (Vals AI) | Not measured | 62.3% | Only Inkling Small measured |
| MedCode (Vals AI) | Not measured | 37.9% | Only Inkling Small measured |
| AA-Omniscience | 16.1 | -9.5 | Inkling 2 Small |
| SimpleQA Verified | Not measured | 19.1% | Only Inkling Small measured |
| LMArena Text: science | 1409 | 1429 | Inkling Small |
| LMArena Text: medicine and healthcare | Not measured | 1414 | Only Inkling Small measured |
| LMArena Text: legal and government | Not measured | 1413 | Only Inkling Small measured |
| LMArena Text: business and finance | 1415 | 1413 | Inkling 2 Small |
| Neither model has a result on the other 9 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Inkling 2 Small | Inkling Small | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index76
| Benchmark | Inkling 2 Small | Inkling Small | Leader |
|---|---|---|---|
| Vals Index | 56.1% | 27.6% | Inkling 2 Small |
| Public Benefits Bench (Vals AI) | Not measured | 59.4% | Only Inkling Small measured |
| SAGE (Vals AI) | 88.6% | Not measured | Only Inkling 2 Small measured |
| MedScribe (Vals AI) | Not measured | 84.1% | Only Inkling Small measured |
| Vals Multimodal Index | Not measured | 50.0% | Only Inkling Small measured |
| Long context reasoning (AA-LCR) | 83.3% | 75.7% | Inkling 2 Small |
| GDPval-AA | 1630 | 1133 | Inkling 2 Small |
| LMArena Text | 1403 | 1414 | Inkling Small |
| LMArena Text: instruction following | 1408 | 1402 | Inkling 2 Small |
| LMArena Text: creative writing | 1348 | 1337 | Inkling 2 Small |
| LMArena Vision | Not measured | 1236 | Only Inkling Small measured |
| LMArena Text: English | 1418 | 1421 | Inkling Small |
| LMArena Text: non-English | 1390 | 1402 | Inkling Small |
| LMArena Text: Chinese | Not measured | 1462 | Only Inkling Small measured |
| LMArena Text: German | Not measured | 1403 | Only Inkling Small measured |
| LMArena Text: Japanese | Not measured | 1397 | Only Inkling Small measured |
| LMArena Text: Korean | Not measured | 1384 | Only Inkling Small measured |
| LMArena Text: French | Not measured | 1438 | Only Inkling Small measured |
| LMArena Text: Spanish | Not measured | 1431 | Only Inkling Small measured |
| LMArena Text: Russian | 1377 | 1397 | Inkling Small |
| LMArena Text: Polish | Not measured | 1427 | Only Inkling Small measured |
| LMArena Text: multi-turn | 1408 | 1417 | Inkling Small |
| LMArena Text: longer queries | 1403 | 1403 | Inkling Small |
| LMArena Text: writing and language | 1381 | 1359 | Inkling 2 Small |
| LMArena Text: entertainment and media | 1359 | 1353 | Inkling 2 Small |
| LMArena Vision: English | Not measured | 1243 | Only Inkling Small measured |
| LMArena Vision: Chinese | Not measured | 1291 | Only Inkling Small measured |
| LMArena Vision: reading text | Not measured | 1242 | Only Inkling Small measured |
| LMArena Vision: humor | Not measured | 1199 | Only Inkling Small measured |
| LMArena Vision: creative writing | Not measured | 1197 | Only Inkling Small measured |
| Neither model has a result on the other 19 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Inkling 2 Small | 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 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 | Thinking Machines Inkling 2 Small | Thinking Machines Inkling Small |
|---|---|---|
| Maker | Thinking Machines | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | November 9, 2026 | July 30, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $0.30 | $0.45 |
| Output $/Mtok | $1.00 | $1.20 |
| Coding index | 48.9 | 27.3 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | Not computable | $0.16 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Inkling 2 Small better than Inkling Small for coding?
Pick Inkling 2 Small for coding: it scores 48.9 on the Vibe Coding Index against 27.3 for Inkling Small, though on 3 benchmarks against 4. Pick Inkling Small for work measured by LMArena Text: software and IT or LMArena Text: hard prompts, where it leads.
Which is cheaper, Inkling 2 Small or Inkling Small?
Inkling 2 Small costs $0.30 per million input tokens and $1.00 per million output tokens; Inkling Small costs $0.45 and $1.20. Cost per solved task is known for Inkling Small only.
Which has the bigger context window, Inkling 2 Small or Inkling Small?
Inkling 2 Small, with 1.05M tokens against 524K.
How many benchmarks is the Inkling 2 Small vs Inkling Small comparison based on?
41 benchmarks have a result for both models as of November 14, 2026. Inkling 2 Small's coding index rests on 3 independent benchmarks and Inkling Small's on 4. Where only one model has a result, the page says so instead of naming a winner.