Compare / Qwen3.5 397B A17B vs Muse Spark 1.3
Qwen3.5 397B A17B vs Muse Spark 1.3
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 1.3 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 24.9% | 57.8% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,445 | 1,479 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,445 | 1,506 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,405 | 1,450 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,476 | 1,527 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,434 | 1,486 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,442 | 1,494 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,421 | 1,466 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 48.2 | 76.5 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 21.4 | 48.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 89.3% | 94.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 29.0% | 48.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 77.3% | 83.0% |
| Artificial Analysisreported | SciCode% of problems | 44.8% | 59.7% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 51.3% | 85.4% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 33.3% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 13.4% | 50.5% |
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.