Muse Spark 1.2 scores 46.6 on the Respan Index (#31), ahead of GPT-5.6 Luna at 46.2 (#33). Muse Spark 1.2 leads on 10 of the 18 benchmarks both report. GPT-5.6 Luna is 4.4x cheaper per token at list price. GPT-5.6 Luna has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Data Analysis (LiveBench) |
| 78% |
| 76.5% |
| LiveBench Instruction Following (LiveBench) | 60.1% | 74.3% |
| LiveBench Language (LiveBench) | 72.6% | 78.6% |
| LiveBench Mathematics (LiveBench) | 87.2% | 91.2% |
| LiveBench Reasoning (LiveBench) | 85.6% | 90% |
| SAGE (Vals AI) | 44.2% | 47.7% |
| SimpleQA Verified | 41% | 60.3% |
| Terminal-Bench 4.0 (Vals AI) | 11.6% | 6.1% |
| WeirdML (Håvard Tveit Ihle) | 60.9% | 60.3% |
| LMArena Agent (LMArena) | -0.0117 | -0.0327 |
| LMArena Elo | 1453 | 1494 |
| LMArena Vision (LMArena) | 1260 | 1293 |
| DeepSWE v1.1 | 67.2% | 59.3% |
| SimpleBench (SimpleBench) | 46.8% | 74.5% |
Higher is better. Each score links to where it was published.