Model comparison
GPT-6 Luna vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 53.3 on the Noometry Index. GPT-6 Luna costs 10× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
MetaSummary
- They share 33 benchmarks with published results for both. GPT-6 Luna scores higher in 2 categories and Muse Spark 1.3 in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Muse Spark 1.3 leads 73.6 to 58.3.
- The biggest single-benchmark swing is Mystery Game Puzzles: 7% for GPT-6 Luna and 25% for Muse Spark 1.3.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1.05M.
Side by side
| GPT-6 Luna | Muse Spark 1.3 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 53.3 | 54.8 |
| Released | 2026-09-22 | 2026-09-02 |
| 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 Muse Spark 1.3 leads
GPT-6 Luna: 55.5 (#25), Muse Spark 1.3: 56.6 (#21)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1581 | 1657 |
| SciCode | 54.6% | 59.7% |
| LMArena Coding | 1439 | 1514 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
| CursorBench | — | 41.6% |
| ALE-Bench | 1,577 | — |
Agentic & Tool Use Muse Spark 1.3 leads
GPT-6 Luna: 33.3 (#54), Muse Spark 1.3: 38.6 (#30)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | 44.3% | 57.8% |
| GDP.pdf | 23% | 27.6% |
Reasoning Muse Spark 1.3 leads
GPT-6 Luna: 48.2 (#41), Muse Spark 1.3: 54.0 (#27)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 68.7% | 85.1% |
| CritPt | 19.4% | 26% |
| Chess Puzzles | 31% | 38% |
| LMArena Hard Prompts | 1411 | 1503 |
| Mystery Game Puzzles | 7% | 25% |
| DTBench | 90.1% | 96.5% |
| LMCA | 44.5% | 53.9% |
| Epoch Capabilities Index | 156.28 | 156.75 |
| ARC-AGI-2 | 59.3% | — |
| ARC-AGI-1 | 86.7% | — |
| Bench to the Future 3 | — | 0.14 |
Math GPT-6 Luna leads
GPT-6 Luna: 76.1 (#15), Muse Spark 1.3: 73.1 (#21)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 78.9% | 74.4% |
| FrontierMath Tier 4 | 56.1% | 46.3% |
| OTIS Mock AIME 2024-2025 | 98.9% | 99.2% |
| ProofBench | 64% | 58% |
| LMArena Math | 1416 | 1494 |
Knowledge GPT-6 Luna leads
GPT-6 Luna: 57.0 (#41), Muse Spark 1.3: 42.6 (#95)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1444 | 1516 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 41.4% | — |
Multimodal Muse Spark 1.3 leads
GPT-6 Luna: 42.4 (#30), Muse Spark 1.3: 43.7 (#22)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1217 | 1309 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 44.2% | — |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
GPT-6 Luna: 50.5 (#117), Muse Spark 1.3: 57.4 (#8)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1386 | 1481 |
| LMArena Chinese | 1433 | 1529 |
| LMArena French | 1420 | 1524 |
| LMArena German | 1369 | 1515 |
| LMArena Japanese | 1369 | 1474 |
| LMArena Korean | 1360 | 1501 |
| LMArena Russian | 1394 | 1490 |
| LMArena Spanish | 1393 | 1490 |
Instruction Following Muse Spark 1.3 leads
GPT-6 Luna: 74.3 (#99), Muse Spark 1.3: 77.5 (#22)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1477 |
Long Context Muse Spark 1.3 leads
GPT-6 Luna: 43.0 (#111), Muse Spark 1.3: 45.6 (#32)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1409 | 1488 |
Writing & Preference Muse Spark 1.3 leads
GPT-6 Luna: 58.3 (#119), Muse Spark 1.3: 73.6 (#9)
| Benchmark | GPT-6 Luna | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1391 | 1490 |
| LMArena Creative Writing | 1363 | 1455 |
| LMArena Multi-Turn | 1396 | 1482 |
| EQ-Bench Creative Writing | — | 1906 |
Frequently asked questions
Is GPT-6 Luna better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 53.3 on the Noometry Index. GPT-6 Luna costs 10× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Luna or Muse Spark 1.3?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is GPT-6 Luna or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 55.5 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 1.3 share?
33 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Muse Spark 1.3 has 37.