GPT-5.6 Sol vs Inkling Small
GPT-5.6 Sol leads Inkling Small on coding, 73.5 to 27.3 on the Vibe Coding Index, and Inkling Small costs 16.7x less per output token ($1.20 vs $20.00 per million). Updated October 22, 2026; 82 benchmarks have a result for both.
GPT-5.6 Sol or Inkling Small: which to pick
Pick GPT-5.6 Sol for coding: it scores 73.5 on the Vibe Coding Index against 27.3 for Inkling Small.
Pick Inkling Small for output tokens 16.7x cheaper ($1.20 vs $20.00 per million) and a lower cost per solved task ($0.16 against $1.20).
- Shared results
- 82
- GPT-5.6 Sol only
- 57
- Inkling Small only
- 2
- 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
GPT-5.6 Sol
GPT-5.6 Sol scores 73.5 against 27.3.
6 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-5.6 Sol
GPT-5.6 Sol leads, 47.0 against 25.7.
Same board, both measured
Agentic work
AA Agentic Index
GPT-5.6 Sol
GPT-5.6 Sol leads, 50.2 against 23.5.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.6 Sol
GPT-5.6 Sol leads, 95.2% against 83.6%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5.6 Sol
GPT-5.6 Sol leads, 89.1% against 85.6%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5.6 Sol has a Design Arena: websites result, 1321.
Directional only
General
Vals Index
No call
Only Inkling Small has a Vals Index result, 27.6%.
Directional only
Long documents
Listed context window
GPT-5.6 Sol
GPT-5.6 Sol takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling Small
GPT-5.6 Sol $0.014, Inkling Small $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Inkling Small
GPT-5.6 Sol $1.20, Inkling Small $0.16.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.6 Sol 73.5 from 6 benchmarks, Inkling Small 27.3 from 4 benchmarks.
- Widest category
- Math, 34.5 points apart on average over 6 shared benchmarks.
- Widest single gap
- IOI (Vals AI): GPT-5.6 Sol 91.2% against Inkling Small 9.3%, 81.8 points apart on a 0 to 100 scale.
- Output price
- GPT-5.6 Sol $20.00 against Inkling Small $1.20 per million output tokens, 16.7x apart.
- Context window
- GPT-5.6 Sol 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 | GPT-5.6 Sol | Bars | Inkling Small | Ties |
|---|---|---|---|---|
| Coding | 17 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 0 | ||
| Reasoning | 12 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 9 | 2 | ||
| General | 28 | 0 | ||
| All shared boards | 79 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index171
| Benchmark | GPT-5.6 Sol | Inkling Small | Leader |
|---|---|---|---|
| LiveBench coding | 89.7% | Not measured | Only GPT-5.6 Sol measured |
| LMArena WebDev | 1616 | 1409 | GPT-5.6 Sol |
| AA Coding Index | 77.4 | 52.9 | GPT-5.6 Sol |
| LiveCodeBench (Vals AI) | 82.6% | 85.9% | Inkling Small |
| SWE-bench Verified (Vals AI) | 96.2% | 82.2% | GPT-5.6 Sol |
| Terminal-Bench 4 (Vals AI) | 37.9% | 0.0% | GPT-5.6 Sol |
| Vibe Code Bench (Vals AI) | 80.5% | 19.1% | GPT-5.6 Sol |
| Code migration (Vals AI) | 52.9% | 13.7% | GPT-5.6 Sol |
| ProgramBench (Vals AI) | 1.5% | 0.5% | GPT-5.6 Sol |
| IOI (Vals AI) | 91.2% | 9.3% | GPT-5.6 Sol |
| Terminal-Bench 2.1 (Vals AI) | 85.8% | 55.1% | GPT-5.6 Sol |
| Vibe Code Bench 1-100 (Vals AI) | 20.0% | Not measured | Only GPT-5.6 Sol measured |
| SkillsBench (Vals AI) | 54.1% | 33.6% | GPT-5.6 Sol |
| CyberBench (Vals AI) | 76.3% | 64.1% | GPT-5.6 Sol |
| SciCode | 57.8% | 49.7% | GPT-5.6 Sol |
| Terminal-Bench Hard (Artificial Analysis run) | 65.9% | Not measured | Only GPT-5.6 Sol measured |
| FrontierCode | 47.5% | Not measured | Only GPT-5.6 Sol measured |
| FrontierSWE | 32.2% | Not measured | Only GPT-5.6 Sol measured |
| GSO-Bench | 76.5% | Not measured | Only GPT-5.6 Sol measured |
| WeirdML | 88.8% | Not measured | Only GPT-5.6 Sol measured |
| MirrorCode | 20.0% | Not measured | Only GPT-5.6 Sol measured |
| ALE-Bench | 2176.9 | Not measured | Only GPT-5.6 Sol measured |
| LMArena Text: coding | 1496 | 1450 | GPT-5.6 Sol |
| LMArena Text: software and IT | 1489 | 1447 | GPT-5.6 Sol |
| LMArena WebDev: React | 1620 | 1399 | GPT-5.6 Sol |
| LMArena WebDev: HTML | 1618 | 1398 | GPT-5.6 Sol |
| LMArena WebDev: from an image | 1609 | 1410 | GPT-5.6 Sol |
| SciCode | 10.8% | Not measured | Only GPT-5.6 Sol measured |
| Neither model has a result on the other 11 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.6 Sol | Inkling Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 47.0 | 25.7 | GPT-5.6 Sol |
| Epoch Capabilities Index | 162.8 | 150.3 | GPT-5.6 Sol |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GPT-5.6 Sol | Inkling Small | Leader |
|---|---|---|---|
| AA Agentic Index | 50.2 | 23.5 | GPT-5.6 Sol |
| Design Arena: agents building web apps | 1245 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: agents building full-stack apps | 1261 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: agents building mobile apps | 1248 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: agents building Android apps | 1240 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: agents building Godot games | 1260 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: agents building games | 1266 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: HTML slides | 1236 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: PowerPoint slides | 1215 | Not measured | Only GPT-5.6 Sol measured |
| LiveBench research | 54.5% | Not measured | Only GPT-5.6 Sol measured |
| LiveBench browser | 88.0% | Not measured | Only GPT-5.6 Sol measured |
| LiveBench long agentic | 48.5% | Not measured | Only GPT-5.6 Sol measured |
| SREBench (Vals AI) | 30.5% | Not measured | Only GPT-5.6 Sol measured |
| Finance Agent (Vals AI) | 53.8% | 41.3% | GPT-5.6 Sol |
| Tax Agent Bench (Vals AI) | 31.1% | 15.4% | GPT-5.6 Sol |
| Legal Research Bench (Vals AI) | 48.1% | 25.5% | GPT-5.6 Sol |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 2.9% | Only Inkling Small measured |
| Excel Modeling Benchmark (Vals AI) | 72.3% | 31.8% | GPT-5.6 Sol |
| BioMysteryBench (Vals AI) | 71.1% | Not measured | Only GPT-5.6 Sol measured |
| Terminal-Bench-Science (Vals AI) | 20.0% | Not measured | Only GPT-5.6 Sol measured |
| Vals Science Index | 41.5% | Not measured | Only GPT-5.6 Sol measured |
| Time Horizon Index (Vals AI) | 23.8% | Not measured | Only GPT-5.6 Sol measured |
| CUA-bench (Vals AI) | 8.3% | Not measured | Only GPT-5.6 Sol measured |
| τ²-Bench Telecom | 85.1% | Not measured | Only GPT-5.6 Sol measured |
| OSWorld 2.0 | 27.3% | Not measured | Only GPT-5.6 Sol measured |
| BALROG | 60.0% | Not measured | Only GPT-5.6 Sol measured |
| PostTrainBench | 36.2% | Not measured | Only GPT-5.6 Sol measured |
| Vending-Bench 2 | $9,619 | Not measured | Only GPT-5.6 Sol measured |
| LMArena Search | 1261 | Not measured | Only GPT-5.6 Sol measured |
| Neither model has a result on the other 12 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
| Benchmark | GPT-5.6 Sol | Inkling Small | Leader |
|---|---|---|---|
| GPQA Diamond | 95.2% | 83.6% | GPT-5.6 Sol |
| LiveBench reasoning | 91.7% | Not measured | Only GPT-5.6 Sol measured |
| MysteryMechanism (Vals AI) | 33.3% | Not measured | Only GPT-5.6 Sol measured |
| MMMU Pro (Vals AI) | 88.8% | Not measured | Only GPT-5.6 Sol measured |
| GPQA Diamond (Artificial Analysis run) | 94.1% | 89.5% | GPT-5.6 Sol |
| Humanity's Last Exam (Artificial Analysis run) | 49.5% | 33.3% | GPT-5.6 Sol |
| GPQA Diamond (Epoch AI run) | 93.5% | 88.5% | GPT-5.6 Sol |
| ARC-AGI | 97.5% | 84.0% | GPT-5.6 Sol |
| ARC-AGI-2 | 92.5% | 40.1% | GPT-5.6 Sol |
| SimpleBench | 64.8% | Not measured | Only GPT-5.6 Sol measured |
| Chess puzzles | 59.0% | Not measured | Only GPT-5.6 Sol measured |
| Mystery game puzzles | 58.0% | 6.0% | GPT-5.6 Sol |
| EBR-bench | 44.8% | Not measured | Only GPT-5.6 Sol measured |
| LMArena Text: hard prompts | 1483 | 1423 | GPT-5.6 Sol |
| LMArena Text: expert | 1517 | 1441 | GPT-5.6 Sol |
| LMArena Text: hard prompts in English | 1477 | 1429 | GPT-5.6 Sol |
| LMArena Vision: diagrams | 1305 | 1251 | GPT-5.6 Sol |
| LMArena Vision: homework | 1305 | 1257 | GPT-5.6 Sol |
| Kagi LLM Benchmark | 67.0% | Not measured | Only GPT-5.6 Sol measured |
| Neither model has a result on the other 3 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GPT-5.6 Sol | Inkling Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 90.0% | GPT-5.6 Sol |
| FrontierMath, tiers 1 to 3 | 89.1% | 46.3% | GPT-5.6 Sol |
| FrontierMath, tier 4 | 82.9% | 17.1% | GPT-5.6 Sol |
| ProofBench | 83.0% | 6.0% | GPT-5.6 Sol |
| LMArena Text: math | 1473 | 1459 | GPT-5.6 Sol |
| LMArena Text: mathematical work | 1496 | 1441 | GPT-5.6 Sol |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index92
| Benchmark | GPT-5.6 Sol | Inkling Small | Leader |
|---|---|---|---|
| MMLU Pro | 89.1% | 85.6% | GPT-5.6 Sol |
| LegalBench (Vals AI) | 87.0% | 83.0% | GPT-5.6 Sol |
| CorpFin (Vals AI) | 64.4% | 69.6% | Inkling Small |
| TaxEval (Vals AI) | 74.8% | 75.5% | Inkling Small |
| MortgageTax (Vals AI) | 67.3% | 62.3% | GPT-5.6 Sol |
| MedCode (Vals AI) | 44.0% | 37.9% | GPT-5.6 Sol |
| SimpleQA Verified | 69.7% | 19.1% | GPT-5.6 Sol |
| LMArena Text: science | 1455 | 1428 | GPT-5.6 Sol |
| LMArena Text: medicine and healthcare | 1431 | 1413 | GPT-5.6 Sol |
| LMArena Text: legal and government | 1476 | 1415 | GPT-5.6 Sol |
| LMArena Text: business and finance | 1457 | 1413 | GPT-5.6 Sol |
| FACTS Benchmark Suite | 52.4% | Not measured | Only GPT-5.6 Sol measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | GPT-5.6 Sol | Inkling Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1321 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: UI components | 1335 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: game dev | 1367 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: data viz | 1322 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: 3D | 1384 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: all code categories | 1341 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: SVG | 1314 | Not measured | Only GPT-5.6 Sol measured |
| Design Arena: ASCII art | 1304 | Not measured | Only GPT-5.6 Sol measured |
| LiveBench design | 81.6% | Not measured | Only GPT-5.6 Sol measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index280
| Benchmark | GPT-5.6 Sol | Inkling Small | Leader |
|---|---|---|---|
| Vals Index | Not measured | 27.6% | Only Inkling Small measured |
| LiveBench data analysis | 79.8% | Not measured | Only GPT-5.6 Sol measured |
| Public Benefits Bench (Vals AI) | 66.5% | 59.4% | GPT-5.6 Sol |
| SAGE (Vals AI) | 52.6% | 32.7% | GPT-5.6 Sol |
| MedScribe (Vals AI) | 85.2% | 84.1% | GPT-5.6 Sol |
| Vals Multimodal Index | 72.6% | 50.0% | GPT-5.6 Sol |
| IFBench | 72.7% | Not measured | Only GPT-5.6 Sol measured |
| Long context reasoning (AA-LCR) | 84.0% | 75.7% | GPT-5.6 Sol |
| DTBench | 95.7% | Not measured | Only GPT-5.6 Sol measured |
| LMCA | 58.5% | Not measured | Only GPT-5.6 Sol measured |
| Surface Evolver Bench | 93.1% | Not measured | Only GPT-5.6 Sol measured |
| Furniture assembly | 56.7% | Not measured | Only GPT-5.6 Sol measured |
| LMArena Text | 1457 | 1413 | GPT-5.6 Sol |
| LMArena Text: instruction following | 1483 | 1399 | GPT-5.6 Sol |
| LMArena Text: creative writing | 1449 | 1334 | GPT-5.6 Sol |
| LMArena Vision | 1281 | 1237 | GPT-5.6 Sol |
| LMArena Text: English | 1457 | 1421 | GPT-5.6 Sol |
| LMArena Text: non-English | 1451 | 1401 | GPT-5.6 Sol |
| LMArena Text: Chinese | 1525 | 1464 | GPT-5.6 Sol |
| LMArena Text: German | 1476 | 1408 | GPT-5.6 Sol |
| LMArena Text: Japanese | 1472 | 1401 | GPT-5.6 Sol |
| LMArena Text: Korean | 1442 | 1367 | GPT-5.6 Sol |
| LMArena Text: French | 1472 | 1435 | GPT-5.6 Sol |
| LMArena Text: Spanish | 1443 | 1422 | GPT-5.6 Sol |
| LMArena Text: Russian | 1471 | 1394 | GPT-5.6 Sol |
| LMArena Text: Polish | 1459 | 1428 | GPT-5.6 Sol |
| LMArena Text: multi-turn | 1461 | 1416 | GPT-5.6 Sol |
| LMArena Text: longer queries | 1481 | 1402 | GPT-5.6 Sol |
| LMArena Text: writing and language | 1462 | 1357 | GPT-5.6 Sol |
| LMArena Text: entertainment and media | 1450 | 1352 | GPT-5.6 Sol |
| LMArena Vision: English | 1280 | 1243 | GPT-5.6 Sol |
| LMArena Vision: Chinese | 1313 | 1292 | GPT-5.6 Sol |
| LMArena Vision: reading text | 1290 | 1243 | GPT-5.6 Sol |
| LMArena Vision: humor | 1246 | 1207 | GPT-5.6 Sol |
| LMArena Vision: creative writing | 1283 | 1205 | GPT-5.6 Sol |
| LMArena Document | 1483 | Not measured | Only GPT-5.6 Sol measured |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.6 Sol | 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 | OpenAI GPT-5.6 Sol | Thinking Machines Inkling Small |
|---|---|---|
| Maker | OpenAI | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | July 9, 2026 | July 30, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $4.00 | $0.45 |
| Output $/Mtok | $20.00 | $1.20 |
| Coding index | 73.5 | 27.3 |
| Independent measurements behind it | 6 | 4 |
| Cost per solved task | $1.20 | $0.16 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.6 Sol better than Inkling Small for coding?
Pick GPT-5.6 Sol for coding: it scores 73.5 on the Vibe Coding Index against 27.3 for Inkling Small. Pick Inkling Small for output tokens 16.7x cheaper ($1.20 vs $20.00 per million) and a lower cost per solved task ($0.16 against $1.20).
Which is cheaper, GPT-5.6 Sol or Inkling Small?
GPT-5.6 Sol costs $4.00 per million input tokens and $20.00 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, GPT-5.6 Sol costs $1.20 and Inkling Small $0.16.
Which has the bigger context window, GPT-5.6 Sol or Inkling Small?
GPT-5.6 Sol, with 1.05M tokens against 524K.
How many benchmarks is the GPT-5.6 Sol vs Inkling Small comparison based on?
82 benchmarks have a result for both models as of October 22, 2026. GPT-5.6 Sol's coding index rests on 6 independent benchmarks and Inkling Small's on 4. Where only one model has a result, the page says so instead of naming a winner.