Hy4 preview and Muse Spark 1.2 tie on the Respan Index at 46.6. Hy4 preview leads on 4 of the 4 benchmarks both report. Hy4 preview is 1.6x cheaper per token at list price. Muse Spark 1.2 has the larger context window (1.0M tokens).
| Benchmark | Hy4 preview | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench 4.0 (Vals AI) | 8.1% | 6.1% |
| LMArena Agent (LMArena) | 0.0395 | -0.0327 |
| LMArena WebDev (LMArena) | 1633 | 1532 |
| Terminal-Bench 2.1 | 85.4% | 82.9% |
Higher is better. Each score links to where it was published.
* Estimated: no published scores in that category. How the Respan Index works