Model comparison
GPT-5.6 Luna vs Inkling-Small
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 46.5 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GPT-5.6 Luna scores higher in 9 categories and Inkling-Small in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 45.1.
- The biggest single-benchmark swing is ProofBench: 60% for GPT-5.6 Luna and 6% for Inkling-Small.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Luna | Inkling-Small | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 54.6 | 46.5 |
| Released | 2026-07-09 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 524K |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $0.20 | $0.45 |
| Output $ / M tokens | $1.20 | $1.20 |
| Results tracked | 52 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GPT-5.6 Luna: 54.5 (#28), Inkling-Small: 43.6 (#85)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1519 | 1409 |
| SciCode | 53.6% | 48.7% |
| LMArena Coding | 1466 | 1451 |
| DeepSWE | 67.2% | — |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Luna: 34.4 (#45), Inkling-Small: —
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| APEX-Agents | 43% | — |
| BALROG | 45.6% | — |
| GDP.pdf | 22.7% | — |
| Vending-Bench 2 | 4,095 | — |
Reasoning GPT-5.6 Luna leads
GPT-5.6 Luna: 47.6 (#43), Inkling-Small: 38.6 (#63)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 59.5% | 40.1% |
| ARC-AGI-1 | 88% | 84% |
| CritPt | 20.6% | 8.3% |
| Chess Puzzles | 40% | 18% |
| LMArena Hard Prompts | 1451 | 1423 |
| Mystery Game Puzzles | 21% | 6% |
| Epoch Capabilities Index | 156.39 | 150.15 |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | 69.4% | — |
| DTBench | 89.1% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | 61.9% | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), Inkling-Small: 45.1 (#77)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.1% | 46.3% |
| FrontierMath Tier 4 | 61% | 17.1% |
| OTIS Mock AIME 2024-2025 | 98.3% | 90% |
| ProofBench | 60% | 6% |
| LMArena Math | 1458 | 1459 |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), Inkling-Small: 48.2 (#77)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| GPQA Diamond | 91.6% | 88.5% |
| SimpleQA Verified | 41% | 19.1% |
| LMArena Expert | 1478 | 1442 |
Multimodal GPT-5.6 Luna leads
GPT-5.6 Luna: 42.7 (#28), Inkling-Small: 39.1 (#62)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| LMArena Vision | 1258 | 1235 |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1457 | — |
Multilingual GPT-5.6 Luna leads
GPT-5.6 Luna: 52.8 (#78), Inkling-Small: 51.7 (#104)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1417 | 1402 |
| LMArena Chinese | 1470 | 1465 |
| LMArena French | 1456 | 1436 |
| LMArena German | 1454 | 1405 |
| LMArena Japanese | 1411 | 1405 |
| LMArena Korean | 1415 | 1363 |
| LMArena Russian | 1428 | 1391 |
| LMArena Spanish | 1448 | 1428 |
Instruction Following GPT-5.6 Luna leads
GPT-5.6 Luna: 75.6 (#57), Inkling-Small: 73.8 (#114)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1437 | 1399 |
Long Context GPT-5.6 Luna leads
GPT-5.6 Luna: 43.9 (#82), Inkling-Small: 42.7 (#118)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1436 | 1401 |
Writing & Preference GPT-5.6 Luna leads
GPT-5.6 Luna: 68.0 (#29), Inkling-Small: 59.6 (#107)
| Benchmark | GPT-5.6 Luna | Inkling-Small |
|---|---|---|
| LMArena Text | 1431 | 1414 |
| LMArena Creative Writing | 1396 | 1331 |
| EQ-Bench Creative Writing | 1829 | 1491 |
| LMArena Multi-Turn | 1434 | 1418 |
| EQ-Bench 4 | 1156 | — |
Frequently asked questions
Is GPT-5.6 Luna better than Inkling-Small?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 46.5 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Inkling-Small?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is GPT-5.6 Luna or Inkling-Small better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 524K.
How many benchmarks do GPT-5.6 Luna and Inkling-Small share?
33 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Inkling-Small has 33.