Muse Spark 1.3 scores 54.1 on the Respan Index (#13), ahead of GPT-5.6 Terra at 53.5 (#14). Muse Spark 1.3 leads on 11 of the 19 benchmarks both report. Muse Spark 1.3 is 2.3x cheaper per token at list price. GPT-5.6 Terra has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Agentic Coding (LiveBench) |
| 54.9% |
| 64.1% |
| LiveBench Coding (LiveBench) | 78.2% | 81.1% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 79.6% |
| LiveBench Instruction Following (LiveBench) | 64.6% | 78% |
| LiveBench Language (LiveBench) | 82.9% | 82.8% |
| LiveBench Mathematics (LiveBench) | 94.9% | 95.9% |
| LiveBench Reasoning (LiveBench) | 90.6% | 89.7% |
| Mystery Game Puzzles (Epoch AI) | 35% | 25% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 99.7% | 99.2% |
| Terminal-Bench 4.0 (Vals AI) | 22.7% | 24.7% |
| LMArena Agent (LMArena) | 0.004 | 0.04 |
| LMArena Elo | 1466 | 1494 |
| LMArena Vision (LMArena) | 1268 | 1290 |
| DeepSWE v1.1 | 69.6% | 75.4% |
| SimpleBench (SimpleBench) | 48.9% | 81.8% |
Higher is better. Each score links to where it was published.