GPT-6 Luna vs Inkling 2 Mini
GPT-6 Luna leads Inkling 2 Mini on coding, 54.9 to 39.5 on the Vibe Coding Index, and Inkling 2 Mini costs 1.5x less per output token ($0.325 vs $0.50 per million). Updated November 22, 2026; 28 benchmarks have a result for both.
GPT-6 Luna or Inkling 2 Mini: which to pick
Pick GPT-6 Luna for coding: it scores 54.9 on the Vibe Coding Index against 39.5 for Inkling 2 Mini.
Pick Inkling 2 Mini for output tokens 1.5x cheaper ($0.325 vs $0.50 per million) and work measured by SWE-bench Multimodal (Vals AI) or Harvey's Legal Agent Benchmark (Vals AI), where it leads.
- Shared results
- 28
- GPT-6 Luna only
- 89
- Inkling 2 Mini 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 Luna
GPT-6 Luna scores 54.9 against 39.5.
5 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-6 Luna
GPT-6 Luna leads, 27.9 against 20.1.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-6 Luna has a Design Arena: websites result, 1264.
Directional only
General
Vals Index
GPT-6 Luna
GPT-6 Luna leads, 52.3% against 46.5%.
Same board, both measured
Long documents
Listed context window
GPT-6 Luna
GPT-6 Luna takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Mini
GPT-6 Luna $0.0003, Inkling 2 Mini $0.0002 per turn.
List prices
At a glance
- Coding index
- GPT-6 Luna 54.9 from 5 benchmarks, Inkling 2 Mini 39.5 from 2 benchmarks.
- Widest category
- Reasoning, 12.0 points apart on average over 3 shared benchmarks.
- Widest single gap
- IOI (Vals AI): GPT-6 Luna 55.6% against Inkling 2 Mini 11.6%, 43.9 points apart on a 0 to 100 scale.
- Output price
- GPT-6 Luna $0.50 against Inkling 2 Mini $0.325 per million output tokens, 1.5x apart.
- Context window
- GPT-6 Luna takes 1.05M tokens, Inkling 2 Mini 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 Luna | Bars | Inkling 2 Mini | Ties |
|---|---|---|---|---|
| Coding | 6 | 1 | 1 tie | |
| Intelligence | 1 | 0 | ||
| Agentic work | 6 | 1 | ||
| Reasoning | 2 | 1 | ||
| Knowledge | 2 | 0 | ||
| Web design | 0 | 3 | ||
| General | 2 | 2 | ||
| All shared boards | 19 | 8 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
| Benchmark | GPT-6 Luna | Inkling 2 Mini | Leader |
|---|---|---|---|
| LiveBench coding | 70.8% | Not measured | Only GPT-6 Luna measured |
| LMArena WebDev | 1578 | Not measured | Only GPT-6 Luna measured |
| Terminal-Bench 4 (Vals AI) | 13.6% | 6.6% | GPT-6 Luna |
| Vibe Code Bench (Vals AI) | 81.7% | 77.9% | GPT-6 Luna |
| Code migration (Vals AI) | 42.5% | Not measured | Only GPT-6 Luna measured |
| ProgramBench (Vals AI) | 0.5% | 0.5% | Tie |
| IOI (Vals AI) | 55.6% | 11.6% | GPT-6 Luna |
| Terminal-Bench 2.1 (Vals AI) | 73.0% | Not measured | Only GPT-6 Luna measured |
| SWE-bench Multimodal (Vals AI) | 37.5% | 37.9% | Inkling 2 Mini |
| SkillsBench (Vals AI) | Not measured | 43.2% | Only Inkling 2 Mini measured |
| CyberBench (Vals AI) | 76.3% | 74.6% | GPT-6 Luna |
| SciCode | 54.6% | Not measured | Only GPT-6 Luna measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 12.6% | 5.6% | GPT-6 Luna |
| FrontierCode 2.0 | 25.2% | 15.1% | GPT-6 Luna |
| FrontierCode | 42.4% | Not measured | Only GPT-6 Luna measured |
| MirrorCode | 26.7% | Not measured | Only GPT-6 Luna measured |
| ALE-Bench | 1576.9 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: coding | 1434 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: software and IT | 1422 | Not measured | Only GPT-6 Luna measured |
| LMArena WebDev: React | 1576 | Not measured | Only GPT-6 Luna measured |
| LMArena WebDev: HTML | 1593 | Not measured | Only GPT-6 Luna measured |
| LMArena WebDev: from an image | 1567 | Not measured | Only GPT-6 Luna measured |
| GameBench 2 | 55.8 | Not measured | Only GPT-6 Luna measured |
| Terminal-Bench 4.0 | 16.4% | Not measured | Only GPT-6 Luna 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 Luna | Inkling 2 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 27.9 | 20.1 | GPT-6 Luna |
| Epoch Capabilities Index | 156.4 | Not measured | Only GPT-6 Luna measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index61
| Benchmark | GPT-6 Luna | Inkling 2 Mini | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1141 | Not measured | Only GPT-6 Luna measured |
| Design Arena: agents building full-stack apps | 1140 | Not measured | Only GPT-6 Luna measured |
| Design Arena: agents building mobile apps | 1115 | Not measured | Only GPT-6 Luna measured |
| Design Arena: agents building Android apps | 1174 | Not measured | Only GPT-6 Luna measured |
| Design Arena: spreadsheets | 871 | Not measured | Only GPT-6 Luna measured |
| LiveBench research | 48.5% | Not measured | Only GPT-6 Luna measured |
| LiveBench browser | 70.3% | Not measured | Only GPT-6 Luna measured |
| LiveBench long agentic | 24.7% | Not measured | Only GPT-6 Luna measured |
| SREBench (Vals AI) | 2.7% | 0.0% | GPT-6 Luna |
| Finance Agent (Vals AI) | 49.9% | Not measured | Only GPT-6 Luna measured |
| Tax Agent Bench (Vals AI) | 19.9% | 14.1% | GPT-6 Luna |
| Legal Research Bench (Vals AI) | 30.3% | 17.8% | GPT-6 Luna |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | 5.0% | Inkling 2 Mini |
| Excel Modeling Benchmark (Vals AI) | 68.5% | Not measured | Only GPT-6 Luna measured |
| BioMysteryBench (Vals AI) | 61.5% | 47.8% | GPT-6 Luna |
| Terminal-Bench-Science (Vals AI) | 4.3% | 0.0% | GPT-6 Luna |
| Vals Science Index | 28.4% | 23.6% | GPT-6 Luna |
| APEX-Agents | 44.3% | Not measured | Only GPT-6 Luna measured |
| SpireClimb | 0.0% | Not measured | Only GPT-6 Luna measured |
| LMArena Search | 1157 | Not measured | Only GPT-6 Luna measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | GPT-6 Luna | Inkling 2 Mini | Leader |
|---|---|---|---|
| LiveBench reasoning | 81.8% | Not measured | Only GPT-6 Luna measured |
| MysteryMechanism (Vals AI) | 19.4% | 23.0% | Inkling 2 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 38.5% | Not measured | Only GPT-6 Luna measured |
| HLE-Diamond (Artificial Analysis run) | 22.2% | 15.2% | GPT-6 Luna |
| CritPt v2, hard subset (Artificial Analysis run) | 42.5% | 17.0% | GPT-6 Luna |
| GPQA Diamond (Epoch AI run) | 90.5% | Not measured | Only GPT-6 Luna measured |
| ARC-AGI | 86.7% | Not measured | Only GPT-6 Luna measured |
| ARC-AGI-2 | 59.3% | Not measured | Only GPT-6 Luna measured |
| Chess puzzles | 36.0% | Not measured | Only GPT-6 Luna measured |
| Mystery game puzzles | 7.0% | Not measured | Only GPT-6 Luna measured |
| LMArena Text: hard prompts | 1408 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: expert | 1437 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: hard prompts in English | 1407 | Not measured | Only GPT-6 Luna measured |
| LMArena Vision: diagrams | 1238 | Not measured | Only GPT-6 Luna measured |
| LMArena Vision: homework | 1257 | Not measured | Only GPT-6 Luna measured |
| GoBench | 1119 | Not measured | Only GPT-6 Luna measured |
| Neither model has a result on the other 10 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-6 Luna | Inkling 2 Mini | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.9% | Not measured | Only GPT-6 Luna measured |
| FrontierMath, tiers 1 to 3 | 78.9% | Not measured | Only GPT-6 Luna measured |
| FrontierMath, tier 4 | 56.1% | Not measured | Only GPT-6 Luna measured |
| ProofBench | 64.0% | Not measured | Only GPT-6 Luna measured |
| LMArena Text: math | 1410 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: mathematical work | 1424 | Not measured | Only GPT-6 Luna measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-6 Luna | Inkling 2 Mini | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 44.7% | 25.7% | GPT-6 Luna |
| AA-Omniscience | -8.3 | -8.6 | GPT-6 Luna |
| SimpleQA Verified | 41.4% | Not measured | Only GPT-6 Luna measured |
| LMArena Text: science | 1387 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: medicine and healthcare | 1353 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: legal and government | 1393 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: business and finance | 1381 | Not measured | Only GPT-6 Luna measured |
| FACTS Benchmark Suite | 64.8% | Not measured | Only GPT-6 Luna measured |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GPT-6 Luna | Inkling 2 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1264 | Not measured | Only GPT-6 Luna measured |
| Design Arena: UI components | 1283 | 1292 | Inkling 2 Mini |
| Design Arena: game dev | 1236 | 1287 | Inkling 2 Mini |
| Design Arena: data viz | 1209 | Not measured | Only GPT-6 Luna measured |
| Design Arena: 3D | 1182 | 1308 | Inkling 2 Mini |
| Design Arena: all code categories | 1254 | Not measured | Only GPT-6 Luna measured |
| Design Arena: SVG | 1230 | Not measured | Only GPT-6 Luna measured |
| Design Arena: ASCII art | 1150 | Not measured | Only GPT-6 Luna measured |
| LiveBench design | 76.1% | Not measured | Only GPT-6 Luna measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | GPT-6 Luna | Inkling 2 Mini | Leader |
|---|---|---|---|
| Vals Index | 52.3% | 46.5% | GPT-6 Luna |
| LiveBench data analysis | 73.4% | Not measured | Only GPT-6 Luna measured |
| Public Benefits Bench (Vals AI) | 57.6% | Not measured | Only GPT-6 Luna measured |
| SAGE (Vals AI) | 83.4% | 85.9% | Inkling 2 Mini |
| MedScribe (Vals AI) | 83.7% | 86.4% | Inkling 2 Mini |
| Long context reasoning (AA-LCR) | 83.3% | Not measured | Only GPT-6 Luna measured |
| GDPval-AA | 1443 | 1319 | GPT-6 Luna |
| DTBench | 90.1% | Not measured | Only GPT-6 Luna measured |
| LMCA | 44.5% | Not measured | Only GPT-6 Luna measured |
| Furniture assembly | 44.2% | Not measured | Only GPT-6 Luna measured |
| LMArena Text | 1390 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: instruction following | 1405 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: creative writing | 1360 | Not measured | Only GPT-6 Luna measured |
| LMArena Vision | 1210 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: English | 1392 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: non-English | 1381 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: Chinese | 1423 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: German | 1381 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: Japanese | 1363 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: Korean | 1349 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: French | 1403 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: Spanish | 1396 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: Russian | 1390 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: Polish | 1381 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: multi-turn | 1395 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: longer queries | 1404 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: writing and language | 1383 | Not measured | Only GPT-6 Luna measured |
| LMArena Text: entertainment and media | 1359 | Not measured | Only GPT-6 Luna measured |
| LMArena Vision: English | 1208 | Not measured | Only GPT-6 Luna measured |
| LMArena Vision: Chinese | 1273 | Not measured | Only GPT-6 Luna measured |
| LMArena Vision: reading text | 1220 | Not measured | Only GPT-6 Luna measured |
| LMArena Vision: humor | 1167 | Not measured | Only GPT-6 Luna measured |
| LMArena Vision: creative writing | 1198 | Not measured | Only GPT-6 Luna measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6 Luna | Inkling 2 Mini | 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 Mini costs less
Repository review
50K input + 3K output tokens
Inkling 2 Mini costs less
Agent loop
200K input + 10K output tokens
Inkling 2 Mini 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 Luna | Thinking Machines Inkling 2 Mini |
|---|---|---|
| Maker | OpenAI | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | September 22, 2026 | November 21, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.10 | $0.0775 |
| Output $/Mtok | $0.50 | $0.325 |
| Coding index | 54.9 | 39.5 |
| Independent measurements behind it | 5 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6 Luna better than Inkling 2 Mini for coding?
Pick GPT-6 Luna for coding: it scores 54.9 on the Vibe Coding Index against 39.5 for Inkling 2 Mini. Pick Inkling 2 Mini for output tokens 1.5x cheaper ($0.325 vs $0.50 per million) and work measured by SWE-bench Multimodal (Vals AI) or Harvey's Legal Agent Benchmark (Vals AI), where it leads.
Which is cheaper, GPT-6 Luna or Inkling 2 Mini?
GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens; Inkling 2 Mini costs $0.0775 and $0.325. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-6 Luna or Inkling 2 Mini?
GPT-6 Luna, with 1.05M tokens against 1.05M.
How many benchmarks is the GPT-6 Luna vs Inkling 2 Mini comparison based on?
28 benchmarks have a result for both models as of November 22, 2026. GPT-6 Luna's coding index rests on 5 independent benchmarks and Inkling 2 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.