Muse Spark 1.3 scores 54.1 on the Respan Index (#13), ahead of GPT-5.5 at 52.5 (#15). Muse Spark 1.3 leads on 8 of the 17 benchmarks both report. Muse Spark 1.3 is 5.6x cheaper per token at list price. Muse Spark 1.3 has the larger context window (1.0M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Agentic Coding (LiveBench) |
| 54% |
| 64.1% |
| LiveBench Coding (LiveBench) | 82.1% | 81.1% |
| LiveBench Data Analysis (LiveBench) | 81.6% | 79.6% |
| LiveBench Instruction Following (LiveBench) | 70.7% | 78% |
| LiveBench Language (LiveBench) | 87.4% | 82.8% |
| LiveBench Mathematics (LiveBench) | 95.9% | 95.9% |
| LiveBench Reasoning (LiveBench) | 89.7% | 89.7% |
| Mystery Game Puzzles (Epoch AI) | 56% | 25% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 84.4% | 99.2% |
| LMArena Agent (LMArena) | 0.0415 | 0.04 |
| LMArena Elo | 1466 | 1494 |
| LMArena Vision (LMArena) | 1287 | 1290 |
| SimpleBench (SimpleBench) | 69% | 81.8% |
Higher is better. Each score links to where it was published.