Model comparison
Muse Spark vs Qwen3-30B-A3B
Muse Spark is the stronger model overall, scoring 50.6 to 38.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Muse Spark scores higher in 8 categories and Qwen3-30B-A3B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 41.8.
- The biggest single-benchmark swing is GPQA Diamond: 89.8% for Muse Spark and 70.1% for Qwen3-30B-A3B.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| Muse Spark | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 50.6 | 38.9 |
| Released | 2026-04-08 | 2025-04-28 |
| Weights | Proprietary | Open |
| Context window | — | 41K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.12 |
| Output $ / M tokens | — | $0.50 |
| Results tracked | 27 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Muse Spark: 46.2 (#69), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 51.5% | 33.3% |
| LMArena Coding | 1481 | 1416 |
| WeirdML | — | 29.8% |
Agentic & Tool Use Not comparable
Muse Spark: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Muse Spark leads
Muse Spark: 35.9 (#67), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 11.3% | 0.3% |
| LMArena Hard Prompts | 1474 | 1398 |
| Epoch Capabilities Index | 152.04 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
Math Muse Spark leads
Muse Spark: 47.8 (#66), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 70.3% |
| LMArena Math | 1455 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| ProofBench | 17% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Muse Spark leads
Muse Spark: 65.7 (#13), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 89.8% | 70.1% |
| LMArena Expert | 1457 | 1396 |
| Humanity's Last Exam | 40.6% | — |
| Confabulations | — | 12.3% |
Multimodal Not comparable
Muse Spark: 43.4 (#24), Qwen3-30B-A3B: —
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |
Multilingual Muse Spark leads
Muse Spark: 56.1 (#24), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1464 | 1372 |
| LMArena Chinese | 1509 | 1433 |
| LMArena French | 1497 | 1418 |
| LMArena German | 1497 | 1380 |
| LMArena Korean | 1459 | 1331 |
| LMArena Russian | 1466 | 1370 |
| LMArena Spanish | 1472 | 1404 |
| LMArena Japanese | — | 1337 |
Instruction Following Muse Spark leads
Muse Spark: 75.9 (#51), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1442 | 1363 |
Long Context Muse Spark leads
Muse Spark: 44.4 (#69), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1451 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Muse Spark leads
Muse Spark: 66.0 (#39), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Muse Spark | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1474 | 1384 |
| LMArena Creative Writing | 1459 | 1317 |
| LMArena Multi-Turn | 1477 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is Muse Spark better than Qwen3-30B-A3B?
Muse Spark is the stronger model overall, scoring 50.6 to 38.9 on the Noometry Index.
Is Muse Spark or Qwen3-30B-A3B better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 37.5 in the Noometry coding category.
How many benchmarks do Muse Spark and Qwen3-30B-A3B share?
21 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Qwen3-30B-A3B has 32.