GPT-6 Sol vs Inkling
Updated October 21, 2026. 82 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick GPT-6 Sol for coding: it scores 82.8 on the Vibe Coding Index against 49.7 for Inkling.
Pick Inkling when output tokens cost 2.5x less, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 82
- GPT-6 Sol only
- 18
- Inkling only
- 20
- Like-for-like categories
- 8 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
GPT-6 Sol
GPT-6 Sol scores 82.8 against 49.7.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-6 Sol
GPT-6 Sol leads, 47.6 against 25.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Inkling has a AA Agentic Index result, 22.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Inkling has a GPQA Diamond result, 87.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Inkling has a MMLU Pro result, 86.3%.
Directional only
Web design
Design Arena: websites
GPT-6 Sol
GPT-6 Sol leads, 1292 against 1224.
Same board, both measured
General
Vals Index
No call
Only Inkling has a Vals Index result, 29.0%.
Directional only
Long documents
Listed context window
GPT-6 Sol
GPT-6 Sol takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling
GPT-6 Sol $0.0070, Inkling $0.0030 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Inkling has the number, $0.76.
Directional only
At a glance
- Coding index
- GPT-6 Sol 82.8 from 2 benchmarks, Inkling 49.7 from 2 benchmarks.
- Widest category
- Math, 42.3 points apart on average over 6 shared benchmarks.
- Widest single gap
- FrontierMath, tier 4: GPT-6 Sol 90.0% against Inkling 4.9%, 85.1 points apart on a 0 to 100 scale.
- Output price
- GPT-6 Sol $10.00 against Inkling $4.05 per million output tokens, 2.5x apart.
- Context window
- GPT-6 Sol takes 1.05M tokens, Inkling 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-6 Sol | Bars | Inkling | Ties |
|---|---|---|---|---|
| Coding | 14 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 9 | 1 | ||
| Reasoning | 6 | 3 | ||
| Math | 4 | 2 | ||
| Knowledge | 2 | 4 | ||
| Web design | 9 | 0 | ||
| General | 5 | 19 | ||
| All shared boards | 51 | 31 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index142
| Benchmark | GPT-6 Sol | Inkling | Leader |
|---|---|---|---|
| LiveBench coding | 93.1% | 64.0% | GPT-6 Sol |
| LMArena WebDev | 1683 | 1414 | GPT-6 Sol |
| AA Coding Index | Not measured | 52.1 | Only Inkling measured |
| LiveCodeBench (Vals AI) | Not measured | 85.5% | Only Inkling measured |
| SWE-bench Verified (Vals AI) | Not measured | 77.6% | Only Inkling measured |
| Terminal-Bench 4 (Vals AI) | 44.4% | 0.5% | GPT-6 Sol |
| Vibe Code Bench (Vals AI) | 87.8% | 19.2% | GPT-6 Sol |
| Code migration (Vals AI) | 57.2% | 11.8% | GPT-6 Sol |
| ProgramBench (Vals AI) | 2.0% | 0.0% | GPT-6 Sol |
| IOI (Vals AI) | 82.6% | 14.9% | GPT-6 Sol |
| Terminal-Bench 2.1 (Vals AI) | 83.2% | 47.6% | GPT-6 Sol |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 7.3% | Only Inkling measured |
| SkillsBench (Vals AI) | Not measured | 26.1% | Only Inkling measured |
| CyberBench (Vals AI) | 78.0% | 66.8% | GPT-6 Sol |
| SciCode | 57.6% | 47.0% | GPT-6 Sol |
| FrontierCode | 49.3% | 14.0% | GPT-6 Sol |
| FrontierSWE | Not measured | 4.1% | Only Inkling measured |
| WeirdML | Not measured | 32.3% | Only Inkling measured |
| ALE-Bench | 2462.0 | 946.0 | GPT-6 Sol |
| LMArena Text: coding | 1448 | 1466 | Inkling |
| LMArena Text: software and IT | 1433 | 1465 | Inkling |
| LMArena WebDev: React | 1685 | 1404 | GPT-6 Sol |
| LMArena WebDev: HTML | 1685 | 1399 | GPT-6 Sol |
| LMArena WebDev: from an image | 1660 | Not measured | Only GPT-6 Sol measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-6 Sol | Inkling | Leader |
|---|---|---|---|
| AA Intelligence Index | 47.6 | 25.0 | GPT-6 Sol |
| Epoch Capabilities Index | 163.7 | 148.4 | GPT-6 Sol |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index91
| Benchmark | GPT-6 Sol | Inkling | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 22.5 | Only Inkling measured |
| Design Arena: agents building web apps | 1232 | 1196 | GPT-6 Sol |
| Design Arena: agents building full-stack apps | 1238 | Not measured | Only GPT-6 Sol measured |
| Design Arena: agents building mobile apps | 1216 | Not measured | Only GPT-6 Sol measured |
| LiveBench research | 69.3% | 59.9% | GPT-6 Sol |
| LiveBench browser | 92.0% | 16.0% | GPT-6 Sol |
| LiveBench long agentic | 66.9% | 14.1% | GPT-6 Sol |
| SREBench (Vals AI) | 30.5% | 0.0% | GPT-6 Sol |
| Finance Agent (Vals AI) | 49.0% | 46.6% | GPT-6 Sol |
| Tax Agent Bench (Vals AI) | 15.0% | 15.3% | Inkling |
| Legal Research Bench (Vals AI) | 28.9% | 28.4% | GPT-6 Sol |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 3.8% | Only Inkling measured |
| Excel Modeling Benchmark (Vals AI) | 71.5% | 38.4% | GPT-6 Sol |
| BioMysteryBench (Vals AI) | 74.8% | Not measured | Only GPT-6 Sol measured |
| Terminal-Bench-Science (Vals AI) | 30.0% | Not measured | Only GPT-6 Sol measured |
| Vals Science Index | 45.0% | Not measured | Only GPT-6 Sol measured |
| APEX-Agents | 54.3% | 33.8% | GPT-6 Sol |
| SpireClimb | 7.5% | Not measured | Only GPT-6 Sol measured |
| Vending-Bench 2 | $14,428 | Not measured | Only GPT-6 Sol measured |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index63
| Benchmark | GPT-6 Sol | Inkling | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 87.1% | Only Inkling measured |
| LiveBench reasoning | 88.7% | 78.3% | GPT-6 Sol |
| MysteryMechanism (Vals AI) | 30.2% | Not measured | Only GPT-6 Sol measured |
| MMMU Pro (Vals AI) | Not measured | 78.5% | Only Inkling measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 87.2% | Only Inkling measured |
| Humanity's Last Exam (Artificial Analysis run) | 47.9% | 31.9% | GPT-6 Sol |
| GPQA Diamond (Epoch AI run) | 94.3% | 88.3% | GPT-6 Sol |
| ARC-AGI | 95.5% | 79.5% | GPT-6 Sol |
| ARC-AGI-2 | 89.6% | 36.5% | GPT-6 Sol |
| SimpleBench | Not measured | 50.0% | Only Inkling measured |
| Chess puzzles | 56.0% | 21.0% | GPT-6 Sol |
| Mystery game puzzles | 56.0% | Not measured | Only GPT-6 Sol measured |
| EBR-bench | 53.3% | Not measured | Only GPT-6 Sol measured |
| LMArena Text: hard prompts | 1422 | 1451 | Inkling |
| LMArena Text: expert | 1437 | 1466 | Inkling |
| LMArena Text: hard prompts in English | 1420 | 1448 | Inkling |
| LMArena Vision: diagrams | 1270 | Not measured | Only GPT-6 Sol measured |
| LMArena Vision: homework | 1286 | Not measured | Only GPT-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 index42
| Benchmark | GPT-6 Sol | Inkling | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 88.9% | GPT-6 Sol |
| FrontierMath, tiers 1 to 3 | 89.8% | 33.3% | GPT-6 Sol |
| FrontierMath, tier 4 | 90.0% | 4.9% | GPT-6 Sol |
| ProofBench | 83.0% | 0.0% | GPT-6 Sol |
| LMArena Text: math | 1407 | 1479 | Inkling |
| LMArena Text: mathematical work | 1424 | 1460 | Inkling |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | GPT-6 Sol | Inkling | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 86.3% | Only Inkling measured |
| LegalBench (Vals AI) | Not measured | 83.0% | Only Inkling measured |
| CorpFin (Vals AI) | Not measured | 68.6% | Only Inkling measured |
| TaxEval (Vals AI) | Not measured | 75.3% | Only Inkling measured |
| MortgageTax (Vals AI) | Not measured | 64.0% | Only Inkling measured |
| MedCode (Vals AI) | 47.1% | 41.2% | GPT-6 Sol |
| SimpleQA Verified | 60.7% | 40.3% | GPT-6 Sol |
| LMArena Text: science | 1389 | 1455 | Inkling |
| LMArena Text: medicine and healthcare | 1366 | 1447 | Inkling |
| LMArena Text: legal and government | 1396 | 1448 | Inkling |
| LMArena Text: business and finance | 1380 | 1438 | Inkling |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | GPT-6 Sol | Inkling | Leader |
|---|---|---|---|
| Design Arena: websites | 1292 | 1224 | GPT-6 Sol |
| Design Arena: UI components | 1292 | 1200 | GPT-6 Sol |
| Design Arena: game dev | 1313 | 1166 | GPT-6 Sol |
| Design Arena: data viz | 1269 | 1160 | GPT-6 Sol |
| Design Arena: 3D | 1322 | 1161 | GPT-6 Sol |
| Design Arena: all code categories | 1301 | 1206 | GPT-6 Sol |
| Design Arena: SVG | 1318 | 1109 | GPT-6 Sol |
| Design Arena: ASCII art | 1226 | 1089 | GPT-6 Sol |
| LiveBench design | 82.2% | 58.3% | GPT-6 Sol |
GeneralLike-for-likePublic boards, shown as published, kept out of the index519
| Benchmark | GPT-6 Sol | Inkling | Leader |
|---|---|---|---|
| Vals Index | Not measured | 29.0% | Only Inkling measured |
| LiveBench data analysis | 81.2% | 72.8% | GPT-6 Sol |
| Public Benefits Bench (Vals AI) | 56.6% | 58.5% | Inkling |
| SAGE (Vals AI) | 44.8% | 36.5% | GPT-6 Sol |
| MedScribe (Vals AI) | 82.0% | 85.4% | Inkling |
| Vals Multimodal Index | Not measured | 49.4% | Only Inkling measured |
| Long context reasoning (AA-LCR) | 83.7% | 77.3% | GPT-6 Sol |
| DTBench | 97.3% | 87.5% | GPT-6 Sol |
| LMCA | 59.1% | 37.6% | GPT-6 Sol |
| Furniture assembly | 58.3% | Not measured | Only GPT-6 Sol measured |
| LMArena Text | 1398 | 1442 | Inkling |
| LMArena Text: instruction following | 1413 | 1425 | Inkling |
| LMArena Text: creative writing | 1378 | 1390 | Inkling |
| LMArena Vision | 1240 | Not measured | Only GPT-6 Sol measured |
| LMArena Text: English | 1396 | 1442 | Inkling |
| LMArena Text: non-English | 1388 | 1434 | Inkling |
| LMArena Text: Chinese | 1412 | 1493 | Inkling |
| LMArena Text: German | 1379 | 1445 | Inkling |
| LMArena Text: Japanese | 1377 | 1429 | Inkling |
| LMArena Text: Korean | 1336 | 1403 | Inkling |
| LMArena Text: French | 1399 | 1455 | Inkling |
| LMArena Text: Spanish | 1387 | 1449 | Inkling |
| LMArena Text: Russian | 1402 | 1430 | Inkling |
| LMArena Text: Polish | 1372 | 1450 | Inkling |
| LMArena Text: multi-turn | 1414 | 1437 | Inkling |
| LMArena Text: longer queries | 1416 | 1435 | Inkling |
| LMArena Text: writing and language | 1389 | 1404 | Inkling |
| LMArena Text: entertainment and media | 1373 | 1394 | Inkling |
| LMArena Vision: English | 1229 | Not measured | Only GPT-6 Sol measured |
| LMArena Vision: reading text | 1258 | Not measured | Only GPT-6 Sol measured |
| LMArena Vision: creative writing | 1219 | Not measured | Only GPT-6 Sol measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6 Sol | Inkling | 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 costs less
Repository review
50K input + 3K output tokens
Inkling costs less
Agent loop
200K input + 10K output tokens
Inkling 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-6 Sol | Thinking Machines Inkling |
|---|---|---|
| Maker | OpenAI | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | September 22, 2026 | July 17, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $2.00 | $1.00 |
| Output $/Mtok | $10.00 | $4.05 |
| Coding index | 82.8 | 49.7 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | Not computable | $0.76 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6 Sol better than Inkling for coding?
Pick GPT-6 Sol for coding: it scores 82.8 on the Vibe Coding Index against 49.7 for Inkling. Pick Inkling when output tokens cost 2.5x less, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, GPT-6 Sol or Inkling?
GPT-6 Sol costs $2.00 per million input tokens and $10.00 per million output tokens; Inkling costs $1.00 and $4.05. Cost per solved task is known for Inkling only.
Which has the bigger context window, GPT-6 Sol or Inkling?
GPT-6 Sol, with 1.05M tokens against 524K.
How many benchmarks is the GPT-6 Sol vs Inkling comparison based on?
82 benchmarks have a result for both models as of October 21, 2026. GPT-6 Sol's coding index rests on 2 independent benchmarks and Inkling's on 2. Where only one model has a result, the page says so instead of naming a winner.