GPT-6 Astra vs Inkling Small
Updated October 21, 2026. 72 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 Astra for coding: it scores 88.7 on the Vibe Coding Index against 29.9 for Inkling Small.
Pick Inkling Small when output tokens cost 41.7x less, or when what matters is CyberBench (Vals AI) or LMArena Text: French, where it leads.
- Shared results
- 72
- GPT-6 Astra only
- 47
- Inkling Small only
- 12
- Like-for-like categories
- 7 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 Astra
GPT-6 Astra scores 88.7 against 29.9.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-6 Astra
GPT-6 Astra leads, 52.7 against 25.7.
Same board, both measured
Agentic work
AA Agentic Index
GPT-6 Astra
GPT-6 Astra leads, 51.0 against 23.5.
Same board, both measured
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
Web design
Design Arena: websites
No call
Only GPT-6 Astra has a Design Arena: websites result, 1337.
Directional only
General
Vals Index
GPT-6 Astra
GPT-6 Astra leads, 65.0% against 27.6%.
Same board, both measured
Long documents
Listed context window
GPT-6 Astra
GPT-6 Astra takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling Small
GPT-6 Astra $0.035, 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
- GPT-6 Astra 88.7 from 2 benchmarks, Inkling Small 29.9 from 1 benchmark.
- Widest category
- Math, 39.9 points apart on average over 6 shared benchmarks.
- Widest single gap
- ProofBench: GPT-6 Astra 99.0% against Inkling Small 6.0%, 93.0 points apart on a 0 to 100 scale.
- Output price
- GPT-6 Astra $50.00 against Inkling Small $1.20 per million output tokens, 41.7x apart.
- Context window
- GPT-6 Astra 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-6 Astra | Bars | Inkling Small | Ties |
|---|---|---|---|---|
| Coding | 14 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 6 | 0 | ||
| Reasoning | 11 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 6 | 0 | ||
| General | 23 | 3 | ||
| All shared boards | 68 | 4 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index141
| Benchmark | GPT-6 Astra | Inkling Small | Leader |
|---|---|---|---|
| LiveBench coding | 93.7% | Not measured | Only GPT-6 Astra measured |
| LMArena WebDev | 1774 | 1409 | GPT-6 Astra |
| AA Coding Index | 76.9 | 52.9 | GPT-6 Astra |
| 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) | 59.6% | 0.0% | GPT-6 Astra |
| Vibe Code Bench (Vals AI) | 89.6% | 19.1% | GPT-6 Astra |
| Code migration (Vals AI) | 67.7% | 13.7% | GPT-6 Astra |
| ProgramBench (Vals AI) | 5.5% | 0.5% | GPT-6 Astra |
| IOI (Vals AI) | 100.0% | 9.3% | GPT-6 Astra |
| Terminal-Bench 2.1 (Vals AI) | 87.3% | 55.1% | GPT-6 Astra |
| SWE-bench Multimodal (Vals AI) | 43.3% | Not measured | Only GPT-6 Astra measured |
| Vibe Code Bench 1-100 (Vals AI) | 27.6% | Not measured | Only GPT-6 Astra measured |
| SkillsBench (Vals AI) | Not measured | 33.6% | Only Inkling Small measured |
| CyberBench (Vals AI) | 41.1% | 64.1% | Inkling Small |
| SciCode | 56.5% | 49.7% | GPT-6 Astra |
| FrontierCode | 53.3% | Not measured | Only GPT-6 Astra measured |
| FrontierSWE | 65.5% | Not measured | Only GPT-6 Astra measured |
| GSO-Bench | 79.4% | Not measured | Only GPT-6 Astra measured |
| WeirdML | 93.3% | Not measured | Only GPT-6 Astra measured |
| MirrorCode | 46.7% | Not measured | Only GPT-6 Astra measured |
| ALE-Bench | 2951.3 | Not measured | Only GPT-6 Astra measured |
| LMArena Text: coding | 1489 | 1450 | GPT-6 Astra |
| LMArena Text: software and IT | 1474 | 1447 | GPT-6 Astra |
| LMArena WebDev: React | 1798 | 1399 | GPT-6 Astra |
| LMArena WebDev: HTML | 1775 | 1398 | GPT-6 Astra |
| LMArena WebDev: from an image | 1726 | 1410 | GPT-6 Astra |
| 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-6 Astra | Inkling Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 52.7 | 25.7 | GPT-6 Astra |
| Epoch Capabilities Index | 168.8 | 150.3 | GPT-6 Astra |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GPT-6 Astra | Inkling Small | Leader |
|---|---|---|---|
| AA Agentic Index | 51.0 | 23.5 | GPT-6 Astra |
| Design Arena: agents building web apps | 1372 | Not measured | Only GPT-6 Astra measured |
| Design Arena: agents building full-stack apps | 1357 | Not measured | Only GPT-6 Astra measured |
| Design Arena: agents building mobile apps | 1312 | Not measured | Only GPT-6 Astra measured |
| Design Arena: agents building Godot games | 1348 | Not measured | Only GPT-6 Astra measured |
| Design Arena: PowerPoint slides | 1245 | Not measured | Only GPT-6 Astra measured |
| Design Arena: spreadsheets | 1380 | Not measured | Only GPT-6 Astra measured |
| LiveBench research | 85.2% | Not measured | Only GPT-6 Astra measured |
| LiveBench browser | 84.0% | Not measured | Only GPT-6 Astra measured |
| LiveBench long agentic | 82.4% | Not measured | Only GPT-6 Astra measured |
| SREBench (Vals AI) | 56.9% | Not measured | Only GPT-6 Astra measured |
| Finance Agent (Vals AI) | 53.5% | 41.3% | GPT-6 Astra |
| Tax Agent Bench (Vals AI) | 20.7% | 15.4% | GPT-6 Astra |
| Legal Research Bench (Vals AI) | 39.4% | 25.5% | GPT-6 Astra |
| Harvey's Legal Agent Benchmark (Vals AI) | 7.1% | 2.9% | GPT-6 Astra |
| Excel Modeling Benchmark (Vals AI) | 71.7% | 31.8% | GPT-6 Astra |
| BioMysteryBench (Vals AI) | 79.3% | Not measured | Only GPT-6 Astra measured |
| Terminal-Bench-Science (Vals AI) | 62.9% | Not measured | Only GPT-6 Astra measured |
| Vals Science Index | 65.1% | Not measured | Only GPT-6 Astra measured |
| Time Horizon Index (Vals AI) | 90.5% | Not measured | Only GPT-6 Astra measured |
| CUA-bench (Vals AI) | 19.2% | Not measured | Only GPT-6 Astra measured |
| Robo-bench (Vals AI) | 23.3% | Not measured | Only GPT-6 Astra measured |
| APEX-Agents | 64.7% | Not measured | Only GPT-6 Astra measured |
| Remote Labor Index | 20.8% | Not measured | Only GPT-6 Astra measured |
| BALROG | 68.3% | Not measured | Only GPT-6 Astra measured |
| SpireClimb | 25.7% | Not measured | Only GPT-6 Astra measured |
| Vending-Bench 2 | $15,515 | Not measured | Only GPT-6 Astra measured |
| Neither model has a result on the other 12 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | GPT-6 Astra | Inkling Small | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 83.6% | Only Inkling Small measured |
| LiveBench reasoning | 92.7% | Not measured | Only GPT-6 Astra measured |
| MysteryMechanism (Vals AI) | 53.1% | Not measured | Only GPT-6 Astra measured |
| GPQA Diamond (Artificial Analysis run) | 96.3% | 89.5% | GPT-6 Astra |
| Humanity's Last Exam (Artificial Analysis run) | 54.7% | 33.3% | GPT-6 Astra |
| GPQA Diamond (Epoch AI run) | 95.8% | 88.5% | GPT-6 Astra |
| ARC-AGI | 98.5% | 84.0% | GPT-6 Astra |
| ARC-AGI-2 | 95.0% | 40.1% | GPT-6 Astra |
| Chess puzzles | 74.0% | Not measured | Only GPT-6 Astra measured |
| Mystery game puzzles | 84.0% | 6.0% | GPT-6 Astra |
| EBR-bench | 76.2% | Not measured | Only GPT-6 Astra measured |
| LMArena Text: hard prompts | 1463 | 1423 | GPT-6 Astra |
| LMArena Text: expert | 1489 | 1441 | GPT-6 Astra |
| LMArena Text: hard prompts in English | 1464 | 1429 | GPT-6 Astra |
| LMArena Vision: diagrams | 1297 | 1251 | GPT-6 Astra |
| LMArena Vision: homework | 1337 | 1257 | GPT-6 Astra |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GPT-6 Astra | Inkling Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 90.0% | GPT-6 Astra |
| FrontierMath, tiers 1 to 3 | 93.7% | 46.3% | GPT-6 Astra |
| FrontierMath, tier 4 | 97.6% | 17.1% | GPT-6 Astra |
| ProofBench | 99.0% | 6.0% | GPT-6 Astra |
| LMArena Text: math | 1465 | 1459 | GPT-6 Astra |
| LMArena Text: mathematical work | 1484 | 1441 | GPT-6 Astra |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | GPT-6 Astra | 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) | 48.5% | 37.9% | GPT-6 Astra |
| SimpleQA Verified | 75.6% | 19.1% | GPT-6 Astra |
| LMArena Text: science | 1451 | 1428 | GPT-6 Astra |
| LMArena Text: medicine and healthcare | 1425 | 1413 | GPT-6 Astra |
| LMArena Text: legal and government | 1462 | 1415 | GPT-6 Astra |
| LMArena Text: business and finance | 1439 | 1413 | GPT-6 Astra |
| 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-6 Astra | Inkling Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1337 | Not measured | Only GPT-6 Astra measured |
| Design Arena: UI components | 1394 | Not measured | Only GPT-6 Astra measured |
| Design Arena: game dev | 1474 | Not measured | Only GPT-6 Astra measured |
| Design Arena: data viz | 1335 | Not measured | Only GPT-6 Astra measured |
| Design Arena: 3D | 1501 | Not measured | Only GPT-6 Astra measured |
| Design Arena: all code categories | 1379 | Not measured | Only GPT-6 Astra measured |
| Design Arena: SVG | 1431 | Not measured | Only GPT-6 Astra measured |
| Design Arena: ASCII art | 1359 | Not measured | Only GPT-6 Astra measured |
| LiveBench design | 82.0% | Not measured | Only GPT-6 Astra measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index233
| Benchmark | GPT-6 Astra | Inkling Small | Leader |
|---|---|---|---|
| Vals Index | 65.0% | 27.6% | GPT-6 Astra |
| LiveBench data analysis | 83.0% | Not measured | Only GPT-6 Astra measured |
| Public Benefits Bench (Vals AI) | Not measured | 59.4% | Only Inkling Small measured |
| SAGE (Vals AI) | 46.4% | 32.7% | GPT-6 Astra |
| MedScribe (Vals AI) | 87.9% | 84.1% | GPT-6 Astra |
| Vals Multimodal Index | Not measured | 50.0% | Only Inkling Small measured |
| Long context reasoning (AA-LCR) | 80.7% | 75.7% | GPT-6 Astra |
| DTBench | 97.3% | Not measured | Only GPT-6 Astra measured |
| LMCA | 64.4% | Not measured | Only GPT-6 Astra measured |
| Furniture assembly | 80.0% | Not measured | Only GPT-6 Astra measured |
| LMArena Text | 1441 | 1413 | GPT-6 Astra |
| LMArena Text: instruction following | 1455 | 1399 | GPT-6 Astra |
| LMArena Text: creative writing | 1420 | 1334 | GPT-6 Astra |
| LMArena Vision | 1280 | 1237 | GPT-6 Astra |
| LMArena Text: English | 1447 | 1421 | GPT-6 Astra |
| LMArena Text: non-English | 1432 | 1401 | GPT-6 Astra |
| LMArena Text: Chinese | 1489 | 1464 | GPT-6 Astra |
| LMArena Text: German | 1459 | 1408 | GPT-6 Astra |
| LMArena Text: Japanese | 1405 | 1401 | GPT-6 Astra |
| LMArena Text: Korean | 1428 | 1367 | GPT-6 Astra |
| LMArena Text: French | 1432 | 1435 | Inkling Small |
| LMArena Text: Spanish | 1422 | 1422 | Inkling Small |
| LMArena Text: Russian | 1438 | 1394 | GPT-6 Astra |
| LMArena Text: Polish | 1422 | 1428 | Inkling Small |
| LMArena Text: multi-turn | 1447 | 1416 | GPT-6 Astra |
| LMArena Text: longer queries | 1460 | 1402 | GPT-6 Astra |
| LMArena Text: writing and language | 1437 | 1357 | GPT-6 Astra |
| LMArena Text: entertainment and media | 1427 | 1352 | GPT-6 Astra |
| LMArena Vision: English | 1280 | 1243 | GPT-6 Astra |
| LMArena Vision: Chinese | 1361 | 1292 | GPT-6 Astra |
| LMArena Vision: reading text | 1292 | 1243 | GPT-6 Astra |
| LMArena Vision: humor | Not measured | 1207 | Only Inkling Small measured |
| LMArena Vision: creative writing | 1286 | 1205 | GPT-6 Astra |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6 Astra | 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-6 Astra | Thinking Machines Inkling Small |
|---|---|---|
| Maker | OpenAI | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | September 4, 2026 | July 30, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $10.00 | $0.45 |
| Output $/Mtok | $50.00 | $1.20 |
| Coding index | 88.7 | 29.9 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | $0.16 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6 Astra better than Inkling Small for coding?
Pick GPT-6 Astra for coding: it scores 88.7 on the Vibe Coding Index against 29.9 for Inkling Small. Pick Inkling Small when output tokens cost 41.7x less, or when what matters is CyberBench (Vals AI) or LMArena Text: French, where it leads.
Which is cheaper, GPT-6 Astra or Inkling Small?
GPT-6 Astra costs $10.00 per million input tokens and $50.00 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, GPT-6 Astra or Inkling Small?
GPT-6 Astra, with 1.05M tokens against 524K.
How many benchmarks is the GPT-6 Astra vs Inkling Small comparison based on?
72 benchmarks have a result for both models as of October 21, 2026. GPT-6 Astra's coding index rests on 2 independent benchmarks and Inkling Small's on 1. Where only one model has a result, the page says so instead of naming a winner.