Gemini 2.5 Pro scores 20.9 on the Respan Index (#90), ahead of Grok 4.3 at 20.7 (#92). Grok 4.3 leads on 6 of the 11 benchmarks both report. Grok 4.3 is 2.2x cheaper per token at list price. Gemini 2.5 Pro has the larger context window (1.0M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 84.7% |
| 93.3% |
| SAGE (Vals AI) | 41.9% | 19.7% |
| Vending-Bench 2 (Andon Labs) | 573.64 | 35.26 |
| WeirdML (Håvard Tveit Ihle) | 54% | 49.9% |
| LMArena Elo | 1458 | 1398 |
| LMArena Vision (LMArena) | 1248 | 1243 |
| LMArena WebDev (LMArena) | 1227 | 1357 |
Higher is better. Each score links to where it was published.