Compare / Muse Spark 1.2 vs GLM 5.2
Muse Spark 1.2 vs GLM 5.2
21 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 1.2 | GLM 5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.05 | 0.04 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.12 | 0.10 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.05 | 0.04 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | 0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,484 | 1,463 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,519 | 1,463 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,448 | 1,455 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,502 | 1,500 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,475 | 1,470 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,496 | 1,476 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,459 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 72.2 | 68.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 39.6 | 33.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 90.4% | 89.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 45.5% | 41.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 79.0% | 78.3% |
| Artificial Analysisreported | SciCode% of problems | 57.4% | 51.2% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 80.2% | 77.9% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 7.1% | 1.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.8% | 34.6% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 60.3% | 34.2% |
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.