Model comparison
GPT-6 Luna vs Muse Spark 1.1
GPT-6 Luna is the stronger model overall, scoring 53.3 to 49.9 on the Noometry Index.
Last verified . 30 shared benchmarks.
MetaSummary
- They share 30 benchmarks with published results for both. GPT-6 Luna scores higher in 5 categories and Muse Spark 1.1 in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 45.5.
- The biggest single-benchmark swing is ProofBench: 64% for GPT-6 Luna and 39% for Muse Spark 1.1.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1.05M.
Side by side
| GPT-6 Luna | Muse Spark 1.1 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 53.3 | 49.9 |
| Released | 2026-09-22 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $1.25 |
| Output $ / M tokens | $0.50 | $4.25 |
| Results tracked | 42 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 55.5 (#25), Muse Spark 1.1: 51.3 (#40)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| DeepSWE | 66.6% | 53.3% |
| LMArena WebDev | 1581 | 1542 |
| SciCode | 54.6% | 58.8% |
| LMArena Coding | 1439 | 1498 |
| FrontierCode | 42.4% | — |
| ALE-Bench | 1,577 | — |
Agentic & Tool Use GPT-6 Luna leads
GPT-6 Luna: 33.3 (#54), Muse Spark 1.1: 30.8 (#73)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| APEX-Agents | 44.3% | 31.8% |
| GDP.pdf | 23% | 15% |
| τ²-bench Banking | — | 40.5% |
| GBAEval | — | 7.9% |
| Vending-Bench 2 | — | 6,520 |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 48.2 (#41), Muse Spark 1.1: 47.1 (#44)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| NYT Connections (extended) | 68.7% | 84.9% |
| CritPt | 19.4% | 15.1% |
| LMArena Hard Prompts | 1411 | 1486 |
| DTBench | 90.1% | 94.4% |
| LMCA | 44.5% | 49.9% |
| Epoch Capabilities Index | 156.28 | 154.21 |
| ARC-AGI-2 | 59.3% | — |
| ARC-AGI-1 | 86.7% | — |
| Chess Puzzles | 31% | — |
| Mystery Game Puzzles | 7% | — |
| Surface Evolver Bench | — | 52.5% |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), Muse Spark 1.1: 45.5 (#76)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| ProofBench | 64% | 39% |
| LMArena Math | 1416 | 1483 |
| FrontierMath (Tiers 1-3) | 78.9% | — |
| FrontierMath Tier 4 | 56.1% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), Muse Spark 1.1: 53.1 (#59)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| SimpleQA Verified | 41.4% | 57.8% |
| LMArena Expert | 1444 | 1478 |
| GPQA Diamond | 90.5% | — |
Multimodal Too close to call
GPT-6 Luna: 42.4 (#30), Muse Spark 1.1: 42.6 (#29)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Vision | 1217 | 1293 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
| LMArena Document | — | 1465 |
Multilingual Muse Spark 1.1 leads
GPT-6 Luna: 50.5 (#117), Muse Spark 1.1: 56.7 (#17)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Non-English | 1386 | 1472 |
| LMArena Chinese | 1433 | 1518 |
| LMArena French | 1420 | 1494 |
| LMArena German | 1369 | 1466 |
| LMArena Japanese | 1369 | 1451 |
| LMArena Korean | 1360 | 1458 |
| LMArena Russian | 1394 | 1483 |
| LMArena Spanish | 1393 | 1464 |
Instruction Following Muse Spark 1.1 leads
GPT-6 Luna: 74.3 (#99), Muse Spark 1.1: 76.5 (#39)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1457 |
Long Context Muse Spark 1.1 leads
GPT-6 Luna: 43.0 (#111), Muse Spark 1.1: 44.8 (#58)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Longer Query | 1409 | 1462 |
Writing & Preference Muse Spark 1.1 leads
GPT-6 Luna: 58.3 (#119), Muse Spark 1.1: 73.4 (#11)
| Benchmark | GPT-6 Luna | Muse Spark 1.1 |
|---|---|---|
| LMArena Text | 1391 | 1479 |
| LMArena Creative Writing | 1363 | 1437 |
| LMArena Multi-Turn | 1396 | 1485 |
| EQ-Bench Creative Writing | — | 1927 |
| EQ-Bench 4 | — | 1260 |
Frequently asked questions
Is GPT-6 Luna better than Muse Spark 1.1?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 49.9 on the Noometry Index.
Which is cheaper, GPT-6 Luna or Muse Spark 1.1?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.
Is GPT-6 Luna or Muse Spark 1.1 better for coding?
GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 51.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-6 Luna and Muse Spark 1.1 share?
30 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Muse Spark 1.1 has 37.