Hy3 scores 37.4 on the Respan Index (#53), ahead of GPT-5 at 37.2 (#54). Hy3 leads on 4 of the 4 benchmarks both report. Hy3 is 15x cheaper per token at list price. GPT-5 has the larger context window (400K tokens).
| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| GPQA Diamond | 86.2% | 90.4% |
| LMArena Elo | 1435 | 1441 |
| LMArena WebDev (LMArena) | 1417 | 1507 |
| SWE-bench Verified | 74.9% | 78% |
Higher is better. Each score links to where it was published.
* Estimated: no published scores in that category. How the Respan Index works