Model comparison
Muse Spark 1.3 vs Qwen2.5-Max
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 40.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Muse Spark 1.3 scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 36.9.
Side by side
| Muse Spark 1.3 | Qwen2.5-Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 54.8 | 40.7 |
| Released | 2026-09-02 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $4.25 | — |
| Results tracked | 37 | 27 |
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), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1514 | 1359 |
| CursorBench | 41.6% | — |
| LMArena WebDev | 1657 | — |
| SciCode | 59.7% | — |
| LiveBench Coding | — | 64.4% |
Agentic & Tool Use Not comparable
Muse Spark 1.3: 38.6 (#30), Qwen2.5-Max: —
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| APEX-Agents | 57.8% | — |
| GDP.pdf | 27.6% | — |
Reasoning Muse Spark 1.3 leads
Muse Spark 1.3: 54.0 (#27), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1503 | 1360 |
| Epoch Capabilities Index | 156.75 | 132.53 |
| NYT Connections (extended) | 85.1% | — |
| CritPt | 26% | — |
| Chess Puzzles | 38% | — |
| LiveBench Reasoning | — | 51.4% |
| Mystery Game Puzzles | 25% | — |
| DTBench | 96.5% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 53.9% | — |
| Bench to the Future 3 | 0.14 | — |
| LiveBench | — | 62.3% |
Math Muse Spark 1.3 leads
Muse Spark 1.3: 73.1 (#21), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1494 | 1369 |
| FrontierMath (Tiers 1-3) | 74.4% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
| ProofBench | 58% | — |
| LiveBench Math | — | 58.4% |
Knowledge Muse Spark 1.3 leads
Muse Spark 1.3: 42.6 (#95), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1516 | 1337 |
| Confabulations | — | 21.8% |
Multimodal Not comparable
Muse Spark 1.3: 43.7 (#22), Qwen2.5-Max: —
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1309 | — |
| LMArena Document | 1471 | — |
Multilingual Muse Spark 1.3 leads
Muse Spark 1.3: 57.4 (#8), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1481 | 1352 |
| LMArena Chinese | 1529 | 1382 |
| LMArena French | 1524 | 1396 |
| LMArena German | 1515 | 1350 |
| LMArena Japanese | 1474 | 1300 |
| LMArena Korean | 1501 | 1304 |
| LMArena Russian | 1490 | 1353 |
| LMArena Spanish | 1490 | 1377 |
Instruction Following Muse Spark 1.3 leads
Muse Spark 1.3: 77.5 (#22), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1477 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Muse Spark 1.3 leads
Muse Spark 1.3: 45.6 (#32), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1488 | 1358 |
Writing & Preference Muse Spark 1.3 leads
Muse Spark 1.3: 73.6 (#9), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Muse Spark 1.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1490 | 1367 |
| LMArena Creative Writing | 1455 | 1339 |
| LMArena Multi-Turn | 1482 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1906 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Muse Spark 1.3 better than Qwen2.5-Max?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 40.7 on the Noometry Index.
Is Muse Spark 1.3 or Qwen2.5-Max better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 41.8 in the Noometry coding category.
How many benchmarks do Muse Spark 1.3 and Qwen2.5-Max share?
18 benchmarks have published results for both models. Muse Spark 1.3 has 37 scored results on Noometry and Qwen2.5-Max has 27.