Compare / Muse Spark 1.1 vs Muse Spark 1.3
Muse Spark 1.1 vs Muse Spark 1.3
22 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 1.1 | Muse Spark 1.3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.02 | 0.08 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.11 | 0.04 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.06 | 0.02 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | 0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,479 | 1,468 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,463 | 1,479 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,493 | 1,506 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,449 | 1,450 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,504 | 1,527 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,473 | 1,486 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,491 | 1,494 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,460 | 1,466 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 71.3 | 76.5 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 33.7 | 48.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 89.8% | 94.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 46.2% | 48.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 77.7% | 83.0% |
| Artificial Analysisreported | SciCode% of problems | 58.8% | 59.7% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 77.9% | 85.4% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 6.1% | 33.3% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 31.8% | 50.5% |
| GDP.pdfreported | Professional document tasks% of rubric | 15.0% | 27.6% |
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.