GPT-6.1 Sol vs Inkling 2 Small
GPT-6.1 Sol leads Inkling 2 Small on coding, 79.8 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; 50 benchmarks have a result for both.
vs boards won of 50 shared
GPT-6.1 Sol or Inkling 2 Small: which to pick
Pick GPT-6.1 Sol for coding: it scores 79.8 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 CyberBench (Vals AI) or SWE-Bench Pro V2, where it leads.
Model AGPT-6.1 SolOpenAI79.8/1005 independent benchmarksNo cost per solved taskModel BInkling 2 SmallThinking Machines48.9/1003 independent benchmarksNo cost per solved task
- Shared results
- 50
- GPT-6.1 Sol only
- 79
- Inkling 2 Small only
- 1
- 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-6.1 Sol
GPT-6.1 Sol scores 79.8 against 48.9.
5 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-6.1 Sol
GPT-6.1 Sol leads, 54.6 against 30.6.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-6.1 Sol has a Design Arena: websites result, 1316.
Directional only
General
Vals Index
GPT-6.1 Sol
GPT-6.1 Sol leads, 63.9% against 56.1%.
Same board, both measured
Long documents
Listed context window
GPT-6.1 Sol
GPT-6.1 Sol takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Small
GPT-6.1 Sol $0.0070, Inkling 2 Small $0.0008 per turn.
List prices
At a glance
- Coding index
- GPT-6.1 Sol 79.8 from 5 benchmarks, Inkling 2 Small 48.9 from 3 benchmarks.
- Widest category
- Math, 38.1 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench 4 (Vals AI): GPT-6.1 Sol 55.0% against Inkling 2 Small 12.6%, 56.6 points apart on a 0 to 100 scale.
- Output price
- GPT-6.1 Sol $10.00 against Inkling 2 Small $1.00 per million output tokens, 10.0x apart.
- Context window
- GPT-6.1 Sol takes 1.05M tokens, Inkling 2 Small 1.05M.
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-6.1 Sol | Bars | Inkling 2 Small | Ties |
|---|---|---|---|---|
| Coding | 12 | 2 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 5 | 3 | ||
| Reasoning | 9 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 3 | 0 | ||
| General | 13 | 1 | ||
| All shared boards | 44 | 6 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index122
| Benchmark | GPT-6.1 Sol | Inkling 2 Small | Leader |
|---|---|---|---|
| LiveBench coding | 82.1% | Not measured | Only GPT-6.1 Sol measured |
| LMArena WebDev | 1743 | 1647 | GPT-6.1 Sol |
| Terminal-Bench 4 (Vals AI) | 55.0% | 12.6% | GPT-6.1 Sol |
| Vibe Code Bench (Vals AI) | 88.9% | 81.5% | GPT-6.1 Sol |
| Code migration (Vals AI) | 65.1% | Not measured | Only GPT-6.1 Sol measured |
| ProgramBench (Vals AI) | 3.0% | 0.5% | GPT-6.1 Sol |
| IOI (Vals AI) | 96.9% | Not measured | Only GPT-6.1 Sol measured |
| SWE-bench Multimodal (Vals AI) | 43.5% | 43.1% | GPT-6.1 Sol |
| CyberBench (Vals AI) | 39.3% | 72.7% | Inkling 2 Small |
| SciCode | 55.8% | 52.3% | GPT-6.1 Sol |
| Terminal-Bench 4.0 (Artificial Analysis run) | 56.1% | 13.1% | GPT-6.1 Sol |
| FrontierCode 2.0 | 40.6% | 25.4% | GPT-6.1 Sol |
| FrontierCode | 50.2% | Not measured | Only GPT-6.1 Sol measured |
| MirrorCode | 61.1% | Not measured | Only GPT-6.1 Sol measured |
| ALE-Bench | 2743.8 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: coding | 1486 | 1455 | GPT-6.1 Sol |
| LMArena Text: software and IT | 1478 | 1443 | GPT-6.1 Sol |
| LMArena WebDev: React | 1747 | 1660 | GPT-6.1 Sol |
| LMArena WebDev: HTML | 1794 | 1661 | GPT-6.1 Sol |
| LMArena WebDev: from an image | 1696 | Not measured | Only GPT-6.1 Sol measured |
| SciCode | 9.2% | Not measured | Only GPT-6.1 Sol measured |
| SWE-Bench Pro V2 | 96.1% | 97.7% | Inkling 2 Small |
| GameBench 2 | 92.0 | Not measured | Only GPT-6.1 Sol measured |
| Terminal-Bench 4.0 | 58.2% | Not measured | Only GPT-6.1 Sol 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 | GPT-6.1 Sol | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 54.6 | 30.6 | GPT-6.1 Sol |
| Epoch Capabilities Index | 168.5 | Not measured | Only GPT-6.1 Sol measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index53
| Benchmark | GPT-6.1 Sol | Inkling 2 Small | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1277 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: agents building mobile apps | 1229 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: agents building Android apps | 1190 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: agents building games | 1195 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: HTML slides | 1485 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: PowerPoint slides | 1304 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: spreadsheets | 1378 | Not measured | Only GPT-6.1 Sol measured |
| LiveBench research | 90.0% | Not measured | Only GPT-6.1 Sol measured |
| LiveBench browser | 93.3% | Not measured | Only GPT-6.1 Sol measured |
| LiveBench long agentic | 65.6% | Not measured | Only GPT-6.1 Sol measured |
| SREBench (Vals AI) | 50.8% | 1.9% | GPT-6.1 Sol |
| Finance Agent (Vals AI) | 52.0% | Not measured | Only GPT-6.1 Sol measured |
| Tax Agent Bench (Vals AI) | 21.8% | 38.9% | Inkling 2 Small |
| Legal Research Bench (Vals AI) | 38.5% | 46.6% | Inkling 2 Small |
| Harvey's Legal Agent Benchmark (Vals AI) | 6.3% | 21.7% | Inkling 2 Small |
| Excel Modeling Benchmark (Vals AI) | 70.8% | Not measured | Only GPT-6.1 Sol measured |
| BioMysteryBench (Vals AI) | 79.6% | 70.0% | GPT-6.1 Sol |
| Terminal-Bench-Science (Vals AI) | 52.9% | 2.9% | GPT-6.1 Sol |
| Vals Science Index | 59.6% | 32.7% | GPT-6.1 Sol |
| Robo-bench (Vals AI) | 28.3% | Not measured | Only GPT-6.1 Sol measured |
| APEX-Agents | 60.0% | 46.8% | GPT-6.1 Sol |
| PostTrainBench | 38.8% | Not measured | Only GPT-6.1 Sol measured |
| SpireClimb | 23.8% | Not measured | Only GPT-6.1 Sol measured |
| Vending-Bench 2 | $12,861 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Search | 1230 | Not measured | Only GPT-6.1 Sol measured |
| MCP Atlas | Not measured | 85.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 18 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | GPT-6.1 Sol | Inkling 2 Small | Leader |
|---|---|---|---|
| LiveBench reasoning | 92.6% | Not measured | Only GPT-6.1 Sol measured |
| MysteryMechanism (Vals AI) | 46.4% | 25.2% | GPT-6.1 Sol |
| Humanity's Last Exam (Artificial Analysis run) | 52.9% | 44.1% | GPT-6.1 Sol |
| HLE-Diamond (Artificial Analysis run) | 58.8% | 28.7% | GPT-6.1 Sol |
| CritPt v2, hard subset (Artificial Analysis run) | 69.5% | 35.0% | GPT-6.1 Sol |
| GPQA Diamond (Epoch AI run) | 95.4% | Not measured | Only GPT-6.1 Sol measured |
| ARC-AGI | 98.5% | 96.5% | GPT-6.1 Sol |
| ARC-AGI-2 | 94.2% | 81.7% | GPT-6.1 Sol |
| SimpleBench | 82.9% | Not measured | Only GPT-6.1 Sol measured |
| Chess puzzles | 68.0% | Not measured | Only GPT-6.1 Sol measured |
| Mystery game puzzles | 80.0% | Not measured | Only GPT-6.1 Sol measured |
| EBR-bench | 54.3% | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: hard prompts | 1466 | 1421 | GPT-6.1 Sol |
| LMArena Text: expert | 1498 | 1478 | GPT-6.1 Sol |
| LMArena Text: hard prompts in English | 1472 | 1424 | GPT-6.1 Sol |
| LMArena Vision: diagrams | 1312 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: homework | 1353 | Not measured | Only GPT-6.1 Sol measured |
| GoBench | 2378 | Not measured | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-6.1 Sol | Inkling 2 Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only GPT-6.1 Sol measured |
| FrontierMath, tiers 1 to 3 | 93.7% | Not measured | Only GPT-6.1 Sol measured |
| FrontierMath, tier 4 | 100.0% | Not measured | Only GPT-6.1 Sol measured |
| ProofBench | 99.0% | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: math | 1475 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: mathematical work | 1498 | Not measured | Only GPT-6.1 Sol measured |
| MathArena | 80.6% | 42.4% | GPT-6.1 Sol |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-6.1 Sol | Inkling 2 Small | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 48.8% | Not measured | Only GPT-6.1 Sol measured |
| AA-Omniscience | 42.4 | 16.1 | GPT-6.1 Sol |
| SimpleQA Verified | 73.9% | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: science | 1457 | 1409 | GPT-6.1 Sol |
| LMArena Text: medicine and healthcare | 1429 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: legal and government | 1472 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: business and finance | 1441 | 1415 | GPT-6.1 Sol |
| FACTS Benchmark Suite | 76.8% | Not measured | Only GPT-6.1 Sol measured |
| PRBench Finance | 46.2% | Not measured | Only GPT-6.1 Sol measured |
| PRBench Legal | 47.9% | Not measured | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-6.1 Sol | Inkling 2 Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1316 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: UI components | 1353 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: game dev | 1407 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: data viz | 1276 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: 3D | 1426 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: all code categories | 1361 | Not measured | Only GPT-6.1 Sol measured |
| Design Arena: SVG | 1343 | Not measured | Only GPT-6.1 Sol measured |
| LiveBench design | 79.6% | Not measured | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index131
| Benchmark | GPT-6.1 Sol | Inkling 2 Small | Leader |
|---|---|---|---|
| Vals Index | 63.9% | 56.1% | GPT-6.1 Sol |
| LiveBench data analysis | 82.7% | Not measured | Only GPT-6.1 Sol measured |
| Public Benefits Bench (Vals AI) | 59.3% | Not measured | Only GPT-6.1 Sol measured |
| SAGE (Vals AI) | 90.5% | 88.6% | GPT-6.1 Sol |
| MedScribe (Vals AI) | 86.5% | Not measured | Only GPT-6.1 Sol measured |
| Long context reasoning (AA-LCR) | 84.0% | 83.3% | GPT-6.1 Sol |
| GDPval-AA | 1607 | 1630 | Inkling 2 Small |
| DTBench | 96.5% | Not measured | Only GPT-6.1 Sol measured |
| LMCA | 62.8% | Not measured | Only GPT-6.1 Sol measured |
| Furniture assembly | 80.0% | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text | 1445 | 1403 | GPT-6.1 Sol |
| LMArena Text: instruction following | 1463 | 1408 | GPT-6.1 Sol |
| LMArena Text: creative writing | 1420 | 1348 | GPT-6.1 Sol |
| LMArena Vision | 1286 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: English | 1451 | 1418 | GPT-6.1 Sol |
| LMArena Text: non-English | 1435 | 1390 | GPT-6.1 Sol |
| LMArena Text: Chinese | 1501 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: German | 1449 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Japanese | 1427 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Korean | 1442 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: French | 1449 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Spanish | 1439 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: Russian | 1452 | 1377 | GPT-6.1 Sol |
| LMArena Text: Polish | 1446 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Text: multi-turn | 1449 | 1408 | GPT-6.1 Sol |
| LMArena Text: longer queries | 1459 | 1403 | GPT-6.1 Sol |
| LMArena Text: writing and language | 1440 | 1381 | GPT-6.1 Sol |
| LMArena Text: entertainment and media | 1421 | 1359 | GPT-6.1 Sol |
| LMArena Vision: English | 1280 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: Chinese | 1340 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: reading text | 1291 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: humor | 1272 | Not measured | Only GPT-6.1 Sol measured |
| LMArena Vision: creative writing | 1292 | Not measured | Only GPT-6.1 Sol measured |
| MultiChallenge | 82.0% | Not measured | Only GPT-6.1 Sol measured |
| EQ-Bench 4 | 1272 | Not measured | Only GPT-6.1 Sol measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6.1 Sol | 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
GPT-6.1 Sol$0.0070Fits in one request
Inkling 2 Small$0.0008Fits in one request
Inkling 2 Small costs less
Repository review
50K input + 3K output tokens
GPT-6.1 Sol$0.130Fits in one request
Inkling 2 Small$0.018Fits in one request
Inkling 2 Small costs less
Agent loop
200K input + 10K output tokens
GPT-6.1 Sol$0.500Fits in one request
Inkling 2 Small$0.070Fits in one request
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 | OpenAI GPT-6.1 Sol | Thinking Machines Inkling 2 Small |
|---|---|---|
| Maker | OpenAI | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | September 29, 2026 | November 9, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $2.00 | $0.30 |
| Output $/Mtok | $10.00 | $1.00 |
| Coding index | 79.8 | 48.9 |
| Independent measurements behind it | 5 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6.1 Sol better than Inkling 2 Small for coding?
Pick GPT-6.1 Sol for coding: it scores 79.8 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 CyberBench (Vals AI) or SWE-Bench Pro V2, where it leads.
Which is cheaper, GPT-6.1 Sol or Inkling 2 Small?
GPT-6.1 Sol 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, GPT-6.1 Sol or Inkling 2 Small?
GPT-6.1 Sol, with 1.05M tokens against 1.05M.
How many benchmarks is the GPT-6.1 Sol vs Inkling 2 Small comparison based on?
50 benchmarks have a result for both models as of November 14, 2026. GPT-6.1 Sol's coding index rests on 5 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.