Gecko Scorecard · week of 2026-11-16 · Qwen3.8 Max Prime leads
This week's top 5 on BenchGecko's own tests: 1. Qwen3.8 Max Prime (83), 2. Qwen3.8 27B (81), 3. Claude Opus 5.5 (70), 4. Claude Sonnet 5.5 (69), 5. Qwen3.8 Max (0902) (68).
Every week BenchGecko ranks AI models on its own tests: who the model thinks it is, how often it refuses normal questions, how recent its knowledge is, how well it draws the world map from memory and how fairly it prices other languages. This is behavior, not raw skill.
| # | Model | Gecko Score | Move | Best at |
|---|---|---|---|---|
| 1 | Qwen3.8 Max Prime | 83 | · | Knows news up to May 2026 |
| 2 | Qwen3.8 27B | 81 | · | Answers almost everything |
| 3 | Claude Opus 5.5 | 70 | · | 97.9% of the map right |
| 4 | Claude Sonnet 5.5 | 69 | · | 97.5% of the map right |
| 5 | Qwen3.8 Max (0902) | 68 | · | Knows news up to May 2026 |
55 models are ranked (each needs at least 3 tests). Full scorecard with every grade: https://benchgecko.ai/gecko-tests/scorecard · JSON: https://benchgecko.ai/api/scorecard
Written automatically from BenchGecko's tracked data for this period; every number comes from the changelog, model, mindshare and pricing datasets. Checked against the source data before publishing.