Model comparison
GPT-6 Sol vs Muse Spark
GPT-6 Sol is the stronger model overall, scoring 61.8 to 50.6 on the Noometry Index.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. GPT-6 Sol scores higher in 5 categories and Muse Spark in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 47.8.
- The biggest single-benchmark swing is ProofBench: 83% for GPT-6 Sol and 17% for Muse Spark.
Side by side
| GPT-6 Sol | Muse Spark | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 61.8 | 50.6 |
| Released | 2026-09-22 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 45 | 27 |
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: 46.2 (#69)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| SciCode | 57.6% | 51.5% |
| LMArena Coding | 1447 | 1481 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1688 | — |
| ALE-Bench | 2,462 | — |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), Muse Spark: —
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| APEX-Agents | 54.3% | — |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Muse Spark: 35.9 (#67)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| CritPt | 30.9% | 11.3% |
| LMArena Hard Prompts | 1418 | 1474 |
| Epoch Capabilities Index | 162.72 | 152.04 |
| ARC-AGI-2 | 89.6% | — |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LMCA | 59.1% | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Muse Spark: 47.8 (#66)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 88.9% |
| ProofBench | 83% | 17% |
| LMArena Math | 1402 | 1455 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Too close to call
GPT-6 Sol: 64.8 (#15), Muse Spark: 65.7 (#13)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| GPQA Diamond | 94.3% | 89.8% |
| LMArena Expert | 1439 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 60.7% | — |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#10), Muse Spark: 43.4 (#24)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| LMArena Vision | 1245 | 1306 |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
GPT-6 Sol: 50.5 (#118), Muse Spark: 56.1 (#24)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| LMArena Non-English | 1385 | 1464 |
| LMArena Chinese | 1405 | 1509 |
| LMArena French | 1410 | 1497 |
| LMArena German | 1390 | 1497 |
| LMArena Korean | 1341 | 1459 |
| LMArena Russian | 1401 | 1466 |
| LMArena Spanish | 1384 | 1472 |
| LMArena Japanese | 1385 | — |
Instruction Following Muse Spark leads
GPT-6 Sol: 74.5 (#94), Muse Spark: 75.9 (#51)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1412 | 1442 |
Long Context Muse Spark leads
GPT-6 Sol: 43.1 (#108), Muse Spark: 44.4 (#69)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1411 | 1451 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Muse Spark: 66.0 (#39)
| Benchmark | GPT-6 Sol | Muse Spark |
|---|---|---|
| LMArena Text | 1395 | 1474 |
| LMArena Creative Writing | 1378 | 1459 |
| LMArena Multi-Turn | 1412 | 1477 |
| EQ-Bench Creative Writing | 2125 | — |
Frequently asked questions
Is GPT-6 Sol better than Muse Spark?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 50.6 on the Noometry Index.
Is GPT-6 Sol or Muse Spark better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 46.2 in the Noometry coding category.
How many benchmarks do GPT-6 Sol and Muse Spark share?
23 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Muse Spark has 27.