Compare / Muse Spark 1.3 vs GPT-5.6 Terra
Muse Spark 1.3 vs GPT-5.6 Terra
23 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 1.3 | GPT-5.6 Terra |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 57.8% | 58.2% |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | 0.08 | -0.06 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | 0.04 | 0.03 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | 0.02 | 0.04 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | 0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,468 | 1,477 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,479 | 1,467 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,506 | 1,466 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,450 | 1,428 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,527 | 1,504 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,486 | 1,462 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,494 | 1,465 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,466 | 1,445 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 76.5 | 76.7 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 48.1 | 42.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 94.1% | 92.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 48.7% | 42.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 83.0% | 83.0% |
| Artificial Analysisreported | SciCode% of problems | 59.7% | 55.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 85.4% | 88.0% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 33.3% | 35.4% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 50.5% | 40.2% |
| GDP.pdfreported | Professional document tasks% of rubric | 27.6% | 24.7% |
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.