Model comparison
Muse Spark 1.2 vs Qwen3-30B-A3B
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 9.3× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Muse Spark 1.2 scores higher in 8 categories and Qwen3-30B-A3B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 21.6.
- The biggest single-benchmark swing is WeirdML: 60.3% for Muse Spark 1.2 and 29.8% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| Muse Spark 1.2 | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 49.8 | 38.5 |
| Released | 2026-08-05 | 2025-04-28 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.25 | $0.12 |
| Output $ / M tokens | $4.25 | $0.50 |
| Results tracked | 28 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Muse Spark 1.2: 48.6 (#49), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 56.4% | 33.3% |
| WeirdML | 60.3% | 29.8% |
| LMArena Coding | 1497 | 1416 |
| DeepSWE | 54.9% | — |
| LMArena WebDev | 1532 | — |
| FrontierSWE | 12% | — |
Agentic & Tool Use Too close to call
Muse Spark 1.2: 29.5 (#77), Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| APEX-Agents | 36.4% | — |
| Berkeley Function Calling Leaderboard | — | 41.4% |
| GDP.pdf | 16% | — |
Reasoning Muse Spark 1.2 leads
Muse Spark 1.2: 50.4 (#32), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 17.7% | 0.3% |
| LMArena Hard Prompts | 1490 | 1398 |
| DTBench | 94.7% | 69.3% |
| LMCA | 48.4% | 22.4% |
| Epoch Capabilities Index | 155.18 | 139.63 |
| SimpleBench | 74.5% | — |
| Kagi LLM Benchmark | — | 54.9% |
| NYT Connections (extended) | 79.2% | — |
| Chess Puzzles | — | 8% |
Math Muse Spark 1.2 leads
Muse Spark 1.2: 43.8 (#68), Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| ProofBench | 43% | — |
| LMArena Math | — | 1394 |
Knowledge Muse Spark 1.2 leads
Muse Spark 1.2: 53.9 (#49), Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1485 | 1395 |
| GPQA Diamond | — | 70.1% |
| SimpleQA Verified | 60.3% | — |
| Confabulations | — | 12.3% |
Multimodal Not comparable
Muse Spark 1.2: 42.6 (#24), Qwen3-30B-A3B: —
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1304 | — |
Multilingual Muse Spark 1.2 leads
Muse Spark 1.2: 57.4 (#10), Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1479 | 1372 |
| LMArena Chinese | 1519 | 1434 |
| LMArena Russian | 1494 | 1369 |
| LMArena French | — | 1419 |
| LMArena German | — | 1379 |
| LMArena Japanese | — | 1338 |
| LMArena Korean | — | 1333 |
| LMArena Spanish | — | 1403 |
Instruction Following Muse Spark 1.2 leads
Muse Spark 1.2: 77.1 (#30), Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1466 | 1364 |
Long Context Muse Spark 1.2 leads
Muse Spark 1.2: 45.4 (#35), Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1483 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Muse Spark 1.2 leads
Muse Spark 1.2: 72.6 (#14), Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | Muse Spark 1.2 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1486 | 1384 |
| LMArena Creative Writing | 1444 | 1318 |
| LMArena Multi-Turn | 1504 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| EQ-Bench Creative Writing | 1840 | — |
Frequently asked questions
Is Muse Spark 1.2 better than Qwen3-30B-A3B?
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 9.3× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Which is cheaper, Muse Spark 1.2 or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Muse Spark 1.2 or Qwen3-30B-A3B better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 37.0 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 41K.
How many benchmarks do Muse Spark 1.2 and Qwen3-30B-A3B share?
17 benchmarks have published results for both models. Muse Spark 1.2 has 28 scored results on Noometry and Qwen3-30B-A3B has 32.