Compare / Muse Spark 1.2 vs GLM 5.1
Muse Spark 1.2 vs GLM 5.1
18 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Muse Spark 1.2 | GLM 5.1 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 36.4% | 40.9% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,484 | 1,456 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,519 | 1,465 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,448 | 1,448 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,502 | 1,495 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,475 | 1,460 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,496 | 1,465 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,453 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 72.2 | 55.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 39.6 | 26.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 90.4% | 86.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 45.5% | 30.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 79.0% | 73.7% |
| Artificial Analysisreported | SciCode% of problems | 57.4% | 44.8% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 80.2% | 61.8% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 7.1% | 2.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.8% | 13.6% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 60.3% | 34.0% |
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.