Muse Spark 1.3 scores 54.1 on the Respan Index (#13), ahead of DeepSeek V4.1 Flash at 50.9 (#20). Muse Spark 1.3 leads on 12 of the 15 benchmarks both report. DeepSeek V4.1 Flash is 3.8x 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 Instruction Following (LiveBench) | 70% | 78% |
| LiveBench Language (LiveBench) | 81.2% | 82.8% |
| LiveBench Mathematics (LiveBench) | 93.3% | 95.9% |
| LiveBench Reasoning (LiveBench) | 86.7% | 89.7% |
| Terminal-Bench 4.0 (Vals AI) | 19.7% | 24.7% |
| LMArena Agent (LMArena) | 0.0402 | 0.04 |
| LMArena Elo | 1474 | 1494 |
| LMArena WebDev (LMArena) | 1620 | 1657 |
| SimpleBench (SimpleBench) | 66.7% | 81.8% |
| DeepSWE v1.1 | 74.2% | 75.4% |
| Terminal-Bench 2.1 | 90.6% | 88.8% |
Higher is better. Each score links to where it was published.