GPT-6 Luna scores 46.8 on the Respan Index (#30), ahead of Hy4 preview at 46.6 (#31). Hy4 preview leads on 3 of the 4 benchmarks both report. GPT-6 Luna is 6.3x cheaper per token at list price. GPT-6 Luna has the larger context window (1.1M tokens).
| Benchmark | GPT-6 Luna | Hy4 preview |
|---|---|---|
| GPQA Diamond | 90.5% | 92.3% |
| Terminal-Bench 4.0 (Vals AI) | 13.6% | 8.1% |
| LMArena Agent (LMArena) | 0.0135 | 0.0395 |
| LMArena WebDev (LMArena) | 1579 | 1633 |
Higher is better. Each score links to where it was published.
* Estimated: no published scores in that category. How the Respan Index works