Model comparison
GPT-5.6 Luna vs Muse Spark 1.1
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 49.9 on the Noometry Index.
Last verified . 35 shared benchmarks.
MetaSummary
- They share 35 benchmarks with published results for both. GPT-5.6 Luna scores higher in 6 categories and Muse Spark 1.1 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 45.5.
- The biggest single-benchmark swing is ProofBench: 60% for GPT-5.6 Luna and 39% for Muse Spark 1.1.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 1.05M.
Side by side
| GPT-5.6 Luna | Muse Spark 1.1 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 54.6 | 49.9 |
| Released | 2026-07-09 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.20 | $1.25 |
| Output $ / M tokens | $1.20 | $4.25 |
| Results tracked | 52 | 37 |
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), Muse Spark 1.1: 51.3 (#40)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| DeepSWE | 67.2% | 53.3% |
| LMArena WebDev | 1519 | 1542 |
| SciCode | 53.6% | 58.8% |
| LMArena Coding | 1466 | 1498 |
| FrontierCode | 39.8% | — |
| CursorBench | 35.9% | — |
| WeirdML | 60.9% | — |
| ALE-Bench | 1,667 | — |
Agentic & Tool Use GPT-5.6 Luna leads
GPT-5.6 Luna: 34.4 (#45), Muse Spark 1.1: 30.8 (#73)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| APEX-Agents | 43% | 31.8% |
| GDP.pdf | 22.7% | 15% |
| Vending-Bench 2 | 4,095 | 6,520 |
| τ²-bench Banking | — | 40.5% |
| BALROG | 45.6% | — |
| GBAEval | — | 7.9% |
Reasoning Too close to call
GPT-5.6 Luna: 47.6 (#43), Muse Spark 1.1: 47.1 (#44)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| NYT Connections (extended) | 69.4% | 84.9% |
| CritPt | 20.6% | 15.1% |
| LMArena Hard Prompts | 1451 | 1486 |
| DTBench | 89.1% | 94.4% |
| LMCA | 48.5% | 49.9% |
| Surface Evolver Bench | 61.9% | 52.5% |
| Epoch Capabilities Index | 156.39 | 154.21 |
| ARC-AGI-2 | 59.5% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 49.1% | — |
| ARC-AGI-1 | 88% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 21% | — |
Math GPT-5.6 Luna leads
GPT-5.6 Luna: 77.7 (#14), Muse Spark 1.1: 45.5 (#76)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| ProofBench | 60% | 39% |
| LMArena Math | 1458 | 1483 |
| FrontierMath (Tiers 1-3) | 82.1% | — |
| FrontierMath Tier 4 | 61% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
Knowledge GPT-5.6 Luna leads
GPT-5.6 Luna: 58.5 (#34), Muse Spark 1.1: 53.1 (#59)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| SimpleQA Verified | 41% | 57.8% |
| LMArena Expert | 1478 | 1478 |
| GPQA Diamond | 91.6% | — |
Multimodal Too close to call
GPT-5.6 Luna: 42.7 (#28), Muse Spark 1.1: 42.6 (#29)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | 1258 | 1293 |
| LMArena Document | 1457 | 1465 |
| Blueprint-Bench 2 | 22.6% | — |
| Furniture Assembly | 42.5% | — |
Multilingual Muse Spark 1.1 leads
GPT-5.6 Luna: 52.8 (#78), Muse Spark 1.1: 56.7 (#17)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | 1417 | 1472 |
| LMArena Chinese | 1470 | 1518 |
| LMArena French | 1456 | 1494 |
| LMArena German | 1454 | 1466 |
| LMArena Japanese | 1411 | 1451 |
| LMArena Korean | 1415 | 1458 |
| LMArena Russian | 1428 | 1483 |
| LMArena Spanish | 1448 | 1464 |
Instruction Following Too close to call
GPT-5.6 Luna: 75.6 (#57), Muse Spark 1.1: 76.5 (#39)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1457 |
Long Context Too close to call
GPT-5.6 Luna: 43.9 (#82), Muse Spark 1.1: 44.8 (#58)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | 1436 | 1462 |
Writing & Preference Muse Spark 1.1 leads
GPT-5.6 Luna: 68.0 (#29), Muse Spark 1.1: 73.4 (#11)
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | 1431 | 1479 |
| LMArena Creative Writing | 1396 | 1437 |
| EQ-Bench Creative Writing | 1829 | 1927 |
| EQ-Bench 4 | 1156 | 1260 |
| LMArena Multi-Turn | 1434 | 1485 |
Frequently asked questions
Is GPT-5.6 Luna better than Muse Spark 1.1?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 49.9 on the Noometry Index.
Which is cheaper, GPT-5.6 Luna or Muse Spark 1.1?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.
Is GPT-5.6 Luna or Muse Spark 1.1 better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 51.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-5.6 Luna and Muse Spark 1.1 share?
35 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Muse Spark 1.1 has 37.