Muse Spark 1.3 scores 54.1 on the Respan Index (#13), ahead of Gemini 3.8 Flash at 52.2 (#16). Muse Spark 1.3 leads on 12 of the 20 benchmarks both report. Gemini 3.8 Flash is 1.3x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Agentic Coding (LiveBench) |
| 54.2% |
| 64.1% |
| LiveBench Coding (LiveBench) | 72.5% | 81.1% |
| LiveBench Data Analysis (LiveBench) | 54% | 79.6% |
| LiveBench Instruction Following (LiveBench) | 81.4% | 78% |
| LiveBench Language (LiveBench) | 87.8% | 82.8% |
| LiveBench Mathematics (LiveBench) | 91.6% | 95.9% |
| LiveBench Reasoning (LiveBench) | 89.3% | 89.7% |
| Mystery Game Puzzles (Epoch AI) | 47% | 25% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.9% | 99.2% |
| Terminal-Bench 4.0 (Vals AI) | 19.2% | 24.7% |
| LMArena Agent (LMArena) | 0.0297 | 0.04 |
| LMArena Elo | 1495 | 1494 |
| LMArena Vision (LMArena) | 1290 | 1290 |
| LMArena WebDev (LMArena) | 1583 | 1657 |
| SimpleBench (SimpleBench) | 82.4% | 81.8% |
| DeepSWE v1.1 | 73.7% | 75.4% |
Higher is better. Each score links to where it was published.