Compare / Muse Spark 1.2 vs Kimi K3
Muse Spark 1.2 vs Kimi K3
23 results from 5 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 | Kimi K3 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 36.4% | 50.6% |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.05 | 0.09 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.12 | 0.07 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.05 | -0.01 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | 0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,484 | 1,472 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,519 | 1,489 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,448 | 1,458 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,502 | 1,533 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,475 | 1,486 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,496 | 1,488 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,475 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 72.2 | 76.2 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 39.6 | 43.6 |
| Artificial Analysisreported | GPQA Diamond% of questions | 90.4% | 93.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 45.5% | 46.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 79.0% | 88.7% |
| Artificial Analysisreported | SciCode% of problems | 57.4% | 59.5% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 80.2% | 85.0% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 7.1% | 12.6% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.8% | 46.0% |
| GDP.pdfreported | Professional document tasks% of rubric | 16.0% | 19.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 60.3% | 50.6% |
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.