GPT-6 Sol scores 62.8 on the Respan Index (#8), ahead of Step 5 Preview at 54.9 (#12). GPT-6 Sol leads on 4 of the 4 benchmarks both report. Step 5 Preview is 2.8x cheaper per token at list price. GPT-6 Sol has the larger context window (1.1M tokens).
| Benchmark | GPT-6 Sol | Step 5 Preview |
|---|---|---|
| Terminal-Bench 4.0 (Vals AI) | 44.4% | 31.8% |
| LMArena Agent (LMArena) | 0.0971 | 0.0048 |
| LMArena Elo | 1457 | 1454 |
| LMArena WebDev (LMArena) | 1689 | 1570 |
Higher is better. Each score links to where it was published.
* Estimated: no published scores in that category. How the Respan Index works