Model comparison
Muse Spark 1.3 vs Qwen3 Max
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 43.7 on the Noometry Index.
Last verified . 25 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Muse Spark 1.3 scores higher in 7 categories and Qwen3 Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 38.7.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 74.4% for Muse Spark 1.3 and 18.9% for Qwen3 Max.
- Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 262K.
Side by side
| Muse Spark 1.3 | Qwen3 Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 54.8 | 43.7 |
| Released | 2026-09-02 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $1.25 | $1.20 |
| Output $ / M tokens | $4.25 | $6 |
| Results tracked | 37 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Muse Spark 1.3: 56.6 (#21), Qwen3 Max: 43.0 (#93)
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1514 | 1456 |
| CursorBench | 41.6% | — |
| LMArena WebDev | 1657 | — |
| SciCode | 59.7% | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
Muse Spark 1.3: 38.6 (#30), Qwen3 Max: —
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| APEX-Agents | 57.8% | — |
| GDP.pdf | 27.6% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Muse Spark 1.3 leads
Muse Spark 1.3: 54.0 (#27), Qwen3 Max: 22.6 (#190)
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 85.1% | 30.1% |
| Chess Puzzles | 38% | 4% |
| LMArena Hard Prompts | 1503 | 1448 |
| Mystery Game Puzzles | 25% | 5% |
| DTBench | 96.5% | 82.1% |
| LMCA | 53.9% | 28.3% |
| Epoch Capabilities Index | 156.75 | 142.38 |
| Kagi LLM Benchmark | — | 72.5% |
| CritPt | 26% | — |
| Bench to the Future 3 | 0.14 | — |
Math Muse Spark 1.3 leads
Muse Spark 1.3: 73.1 (#21), Qwen3 Max: 38.7 (#131)
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74.4% | 18.9% |
| OTIS Mock AIME 2024-2025 | 99.2% | 73.3% |
| LMArena Math | 1494 | 1446 |
| FrontierMath Tier 4 | 46.3% | — |
| ProofBench | 58% | — |
| MATH Level 5 | — | 97.1% |
Knowledge Qwen3 Max leads
Muse Spark 1.3: 42.6 (#95), Qwen3 Max: 48.1 (#78)
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1516 | 1455 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |
Multimodal Not comparable
Muse Spark 1.3: 43.7 (#22), Qwen3 Max: —
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1309 | — |
| LMArena Document | 1471 | — |
Multilingual Muse Spark 1.3 leads
Muse Spark 1.3: 57.4 (#8), Qwen3 Max: 53.7 (#62)
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1481 | 1429 |
| LMArena Chinese | 1529 | 1478 |
| LMArena French | 1524 | 1449 |
| LMArena German | 1515 | 1463 |
| LMArena Japanese | 1474 | 1397 |
| LMArena Korean | 1501 | 1399 |
| LMArena Russian | 1490 | 1428 |
| LMArena Spanish | 1490 | 1462 |
Instruction Following Muse Spark 1.3 leads
Muse Spark 1.3: 77.5 (#22), Qwen3 Max: 74.8 (#87)
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1477 | 1419 |
Long Context Muse Spark 1.3 leads
Muse Spark 1.3: 45.6 (#32), Qwen3 Max: 41.6 (#134)
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1488 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Muse Spark 1.3 leads
Muse Spark 1.3: 73.6 (#9), Qwen3 Max: 62.4 (#76)
| Benchmark | Muse Spark 1.3 | Qwen3 Max |
|---|---|---|
| LMArena Text | 1490 | 1439 |
| LMArena Creative Writing | 1455 | 1402 |
| LMArena Multi-Turn | 1482 | 1446 |
| EQ-Bench Creative Writing | 1906 | — |
Frequently asked questions
Is Muse Spark 1.3 better than Qwen3 Max?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 43.7 on the Noometry Index.
Which is cheaper, Muse Spark 1.3 or Qwen3 Max?
Muse Spark 1.3 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Muse Spark 1.3 or Qwen3 Max better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 43.0 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 262K.
How many benchmarks do Muse Spark 1.3 and Qwen3 Max share?
25 benchmarks have published results for both models. Muse Spark 1.3 has 37 scored results on Noometry and Qwen3 Max has 33.