Gemini 3.1 Flash-Lite scores 25.2 on the Respan Index (#80), ahead of Qwen3.6 35B-A3B at 24.9 (#82). Gemini 3.1 Flash-Lite leads on 3 of the 5 benchmarks both report. Gemini 3.1 Flash-Lite has the larger context window (1.0M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| WeirdML (Håvard Tveit Ihle) |
| 52.2% |
| 34.5% |
Higher is better. Each score links to where it was published.