Model comparison
Muse Spark 1.2 vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 50.3 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Muse Spark 1.2 scores higher in 6 categories and Qwen3.6 Max Preview in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 41.7.
- The biggest single-benchmark swing is SimpleBench: 74.5% for Muse Spark 1.2 and 63% for Qwen3.6 Max Preview.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.
Side by side
| Muse Spark 1.2 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 50.3 | 51.5 |
| Released | 2026-08-05 | 2026-04-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $1.25 | $1.30 |
| Output $ / M tokens | $4.25 | $7.80 |
| Results tracked | 31 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Muse Spark 1.2: 49.2 (#51), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1533 | 1482 |
| LMArena Coding | 1495 | 1471 |
| SWE-bench Verified | — | 76.7% |
| DeepSWE | 54.9% | — |
| FrontierSWE | 12% | — |
| SciCode | 56.4% | — |
| WeirdML | 60.3% | — |
Agentic & Tool Use Not comparable
Muse Spark 1.2: 29.4 (#87), Qwen3.6 Max Preview: —
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| APEX-Agents | 36.4% | — |
| GDP.pdf | 16% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Muse Spark 1.2 leads
Muse Spark 1.2: 51.3 (#34), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 74.5% | 63% |
| NYT Connections (extended) | 79.2% | 74.1% |
| LMArena Hard Prompts | 1486 | 1457 |
| DTBench | 94.7% | 87.2% |
| LMCA | 48.4% | 42.5% |
| Epoch Capabilities Index | 154.87 | 149.24 |
| CritPt | 17.7% | — |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
Math Qwen3.6 Max Preview leads
Muse Spark 1.2: 46.4 (#70), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1471 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| ProofBench | 43% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Muse Spark 1.2: 54.1 (#53), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| SimpleQA Verified | 60.3% | 52% |
| LMArena Expert | 1480 | 1478 |
| GPQA Diamond | — | 87.4% |
Multimodal Not comparable
Muse Spark 1.2: 43.4 (#25), Qwen3.6 Max Preview: —
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1305 | — |
Multilingual Muse Spark 1.2 leads
Muse Spark 1.2: 57.1 (#11), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1478 | 1437 |
| LMArena Chinese | 1511 | 1487 |
| LMArena French | 1513 | 1449 |
| LMArena Russian | 1487 | 1445 |
| LMArena Spanish | 1498 | 1454 |
Instruction Following Muse Spark 1.2 leads
Muse Spark 1.2: 76.7 (#36), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1461 | 1438 |
Long Context Too close to call
Muse Spark 1.2: 45.2 (#48), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1475 | 1457 |
Writing & Preference Muse Spark 1.2 leads
Muse Spark 1.2: 72.3 (#14), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Muse Spark 1.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1482 | 1447 |
| LMArena Creative Writing | 1449 | 1435 |
| LMArena Multi-Turn | 1494 | 1456 |
| EQ-Bench Creative Writing | 1840 | — |
Frequently asked questions
Is Muse Spark 1.2 better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 50.3 on the Noometry Index.
Which is cheaper, Muse Spark 1.2 or Qwen3.6 Max Preview?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Muse Spark 1.2 or Qwen3.6 Max Preview better for coding?
They score almost the same on coding (49.2 vs 48.7); test both on your own repository before choosing.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 262K.
How many benchmarks do Muse Spark 1.2 and Qwen3.6 Max Preview share?
21 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and Qwen3.6 Max Preview has 29.