Compare / Muse Spark 1.3 vs GLM 5.1
Muse Spark 1.3 vs GLM 5.1
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 | Muse Spark 1.3 | GLM 5.1 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 57.8% | 40.9% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,479 | 1,456 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,506 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,450 | 1,448 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,527 | 1,495 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,486 | 1,460 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,494 | 1,465 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,466 | 1,453 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 76.5 | 55.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 48.1 | 26.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 94.1% | 86.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 48.7% | 30.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 83.0% | 73.7% |
| Artificial Analysisreported | SciCode% of problems | 59.7% | 44.8% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 85.4% | 61.8% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 33.3% | 2.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 50.5% | 13.6% |
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.