Model comparison
GPT-6 Sol vs Muse Spark 1.2
GPT-6 Sol is the stronger model overall, scoring 61.8 to 50.3 on the Noometry Index. Muse Spark 1.2 costs 2.0× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
MetaSummary
- They share 28 benchmarks with published results for both. GPT-6 Sol scores higher in 6 categories and Muse Spark 1.2 in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 46.4.
- The biggest single-benchmark swing is ProofBench: 83% for GPT-6 Sol and 43% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1.05M.
Side by side
| GPT-6 Sol | Muse Spark 1.2 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 61.8 | 50.3 |
| Released | 2026-09-22 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $10 | $4.25 |
| Results tracked | 45 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), Muse Spark 1.2: 49.2 (#51)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| DeepSWE | 68.8% | 54.9% |
| LMArena WebDev | 1688 | 1533 |
| SciCode | 57.6% | 56.4% |
| LMArena Coding | 1447 | 1495 |
| FrontierCode | 49.3% | — |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
| ALE-Bench | 2,462 | — |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 37.2 (#36), Muse Spark 1.2: 29.4 (#87)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | 54.3% | 36.4% |
| GDP.pdf | 26.4% | 16% |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Muse Spark 1.2: 51.3 (#34)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| NYT Connections (extended) | 90.1% | 79.2% |
| CritPt | 30.9% | 17.7% |
| LMArena Hard Prompts | 1418 | 1486 |
| DTBench | 97.3% | 94.7% |
| LMCA | 59.1% | 48.4% |
| Epoch Capabilities Index | 162.72 | 154.87 |
| ARC-AGI-2 | 89.6% | — |
| SimpleBench | — | 74.5% |
| ARC-AGI-1 | 95.5% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Muse Spark 1.2: 46.4 (#70)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 83% | 43% |
| LMArena Math | 1402 | 1471 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Muse Spark 1.2: 54.1 (#53)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 60.7% | 60.3% |
| LMArena Expert | 1439 | 1480 |
| GPQA Diamond | 94.3% | — |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#10), Muse Spark 1.2: 43.4 (#25)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1245 | 1305 |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual Muse Spark 1.2 leads
GPT-6 Sol: 50.5 (#118), Muse Spark 1.2: 57.1 (#11)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1385 | 1478 |
| LMArena Chinese | 1405 | 1511 |
| LMArena French | 1410 | 1513 |
| LMArena Russian | 1401 | 1487 |
| LMArena Spanish | 1384 | 1498 |
| LMArena German | 1390 | — |
| LMArena Japanese | 1385 | — |
| LMArena Korean | 1341 | — |
Instruction Following Muse Spark 1.2 leads
GPT-6 Sol: 74.5 (#94), Muse Spark 1.2: 76.7 (#36)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1412 | 1461 |
Long Context Muse Spark 1.2 leads
GPT-6 Sol: 43.1 (#108), Muse Spark 1.2: 45.2 (#48)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1411 | 1475 |
Writing & Preference Too close to call
GPT-6 Sol: 71.9 (#18), Muse Spark 1.2: 72.3 (#14)
| Benchmark | GPT-6 Sol | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1395 | 1482 |
| LMArena Creative Writing | 1378 | 1449 |
| EQ-Bench Creative Writing | 2125 | 1840 |
| LMArena Multi-Turn | 1412 | 1494 |
Frequently asked questions
Is GPT-6 Sol better than Muse Spark 1.2?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 50.3 on the Noometry Index. Muse Spark 1.2 costs 2.0× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Sol or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Muse Spark 1.2 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 49.2 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-6 Sol and Muse Spark 1.2 share?
28 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Muse Spark 1.2 has 31.