Claude 3.5 Sonnet scores 14.4 on the Respan Index (#125), ahead of GPT-4.1 mini at 14.3 (#127). GPT-4.1 mini leads on 5 of the 6 benchmarks both report. GPT-4.1 mini is 8.6x cheaper per token at list price. GPT-4.1 mini has the larger context window (1.0M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 1374 |
| 1383 |
| LMArena Vision (LMArena) | 1161 | 1201 |
Higher is better. Each score links to where it was published.