Muse Spark vs Qwen3.8 Max (0902)
Muse Spark 
Qwen3.8 Max (0902) Verdict
- Muse Spark leads on quality: 65.2 vs 57.1.
- Muse Spark is stronger in agents & tools, coding, human preference, instruction following, knowledge, multimodal, reasoning.
- Qwen3.8 Max (0902) (xhigh) is stronger in maths.
| Metric | Muse Spark | Qwen3.8 Max (0902) (xhigh) |
|---|---|---|
| BenchLeader Index | 65.2 | 57.1 |
| Agents & tools score | 62.9 | – |
| Coding score | 66.2 | – |
| Human preference score | 69.2 | – |
| Instruction following score | 83.8 | – |
| Knowledge score | 63.8 | 55.9 |
| Maths score | 56.4 | 61.2 |
| Multimodal score | 66.7 | – |
| Reasoning score | 70.2 | 66.9 |
| Blended price $/M | – | $3.00 |
| Output speed | – | 38 tok/s |
| Time to first answer | – | 2.0 s |
| Context window | – | 1M |
| GPQA Diamond | 89.8% | 92.3% |
| FrontierMath Tiers 1–3 | – | 65.6% |
| FrontierMath Tier 4 | – | 34.1% |
| OTIS Mock AIME | 88.9% | 100.0% |
| SimpleQA Verified | – | 47.3% |
| Humanity's Last Exam | 40.6% | – |
| SciCode | 51.5% | – |
| ProofBench | 17.0% | – |
| Epoch Capabilities Index | 152.1 | – |
| LMArena Text | 1488 | – |
| LMArena Hard Prompts | 1505 | – |
| LMArena Coding | 1526 | – |
| LMArena Vision | 1306 | – |
| AIME (Vals) | 96.9% | – |
| MMLU-Pro | 87.3% | – |
| LegalBench | 84.2% | – |
| CorpFin | 65.1% | – |
| TaxEval | 77.7% | – |
| SWE-bench (Vals) | 74.4% | – |
| GPQA Diamond (Vals) | 89.7% | – |
| SWE-Bench Pro | 55.0% | – |
| MCP Atlas | 82.2% | – |
| MultiChallenge | 75.5% | – |
| PRBench Finance | 52.4% | – |
| PRBench Legal | 52.3% | – |
| MultiNRC | 59.0% | – |
| TutorBench | 68.5% | – |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Muse Spark vs Qwen3.8 Max (0902): questions
- Is Muse Spark better than Qwen3.8 Max (0902)?
- Muse Spark leads on quality: 65.2 vs 57.1. The BenchLeader Index combines every independent quality benchmark; Muse Spark is ahead overall as of 2026-09-13, but check the category scores for your use.