Compare / Qwen3.5 397B A17B vs Muse Spark 1.2
Qwen3.5 397B A17B vs Muse Spark 1.2
17 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3.5 397B A17B | Muse Spark 1.2 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 24.9% | 36.4% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,445 | 1,484 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,445 | 1,519 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,405 | 1,448 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,476 | 1,502 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,434 | 1,475 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,442 | 1,496 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,421 | 1,472 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 48.2 | 72.2 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 21.4 | 39.6 |
| Artificial Analysisreported | GPQA Diamond% of questions | 89.3% | 90.4% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 29.0% | 45.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 77.3% | 79.0% |
| Artificial Analysisreported | SciCode% of problems | 44.8% | 57.4% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 51.3% | 80.2% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 7.1% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 13.4% | 34.8% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.