Model comparison
Muse Spark vs Qwen3 Max
Muse Spark is the stronger model overall, scoring 50.6 to 43.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Muse Spark scores higher in 8 categories and Qwen3 Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 48.1.
- The biggest single-benchmark swing is GPQA Diamond: 89.8% for Muse Spark and 72.6% for Qwen3 Max.
Side by side
| Muse Spark | Qwen3 Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 50.6 | 43.7 |
| Released | 2026-04-08 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.20 |
| Output $ / M tokens | — | $6 |
| Results tracked | 27 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Muse Spark: 46.2 (#69), Qwen3 Max: 43.0 (#93)
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1481 | 1456 |
| SciCode | 51.5% | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
Muse Spark: —, Qwen3 Max: —
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | — | 71.56 |
Reasoning Muse Spark leads
Muse Spark: 35.9 (#67), Qwen3 Max: 22.6 (#190)
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| LMArena Hard Prompts | 1474 | 1448 |
| Epoch Capabilities Index | 152.04 | 142.38 |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| CritPt | 11.3% | — |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |
Math Muse Spark leads
Muse Spark: 47.8 (#66), Qwen3 Max: 38.7 (#131)
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 73.3% |
| LMArena Math | 1455 | 1446 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| ProofBench | 17% | — |
| MATH Level 5 | — | 97.1% |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Muse Spark leads
Muse Spark: 65.7 (#13), Qwen3 Max: 48.1 (#78)
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 89.8% | 72.6% |
| LMArena Expert | 1457 | 1455 |
| Humanity's Last Exam | 40.6% | — |
| SimpleQA Verified | — | 48.7% |
Multimodal Not comparable
Muse Spark: 43.4 (#24), Qwen3 Max: —
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |
Multilingual Muse Spark leads
Muse Spark: 56.1 (#24), Qwen3 Max: 53.7 (#62)
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1464 | 1429 |
| LMArena Chinese | 1509 | 1478 |
| LMArena French | 1497 | 1449 |
| LMArena German | 1497 | 1463 |
| LMArena Korean | 1459 | 1399 |
| LMArena Russian | 1466 | 1428 |
| LMArena Spanish | 1472 | 1462 |
| LMArena Japanese | — | 1397 |
Instruction Following Muse Spark leads
Muse Spark: 75.9 (#51), Qwen3 Max: 74.8 (#87)
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1442 | 1419 |
Long Context Muse Spark leads
Muse Spark: 44.4 (#69), Qwen3 Max: 41.6 (#134)
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1451 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Muse Spark leads
Muse Spark: 66.0 (#39), Qwen3 Max: 62.4 (#76)
| Benchmark | Muse Spark | Qwen3 Max |
|---|---|---|
| LMArena Text | 1474 | 1439 |
| LMArena Creative Writing | 1459 | 1402 |
| LMArena Multi-Turn | 1477 | 1446 |
Frequently asked questions
Is Muse Spark better than Qwen3 Max?
Muse Spark is the stronger model overall, scoring 50.6 to 43.7 on the Noometry Index.
Is Muse Spark or Qwen3 Max better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 43.0 in the Noometry coding category.
How many benchmarks do Muse Spark and Qwen3 Max share?
19 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Qwen3 Max has 33.