Models · Edition 1.1
Models tested in edition 1.1.
20 models have an official result in this edition. Each summary shows the model's results by subject and links to every round.
For the ranked comparison, see the results overview.
All models, A to Z
| Model | Rank | Question score | Rounds solved |
|---|---|---|---|
| Claude Fable 5.1High | Rank 5 | 15.10 | 28 of 30 |
| Claude Opus 5High | Rank 11 | 18.07 | 28 of 30 |
| Claude Opus 5.5High | Rank 4 | 15.00 | 29 of 30 |
| Claude Sonnet 5.5High | Rank 9 | 17.83 | 27 of 30 |
| Gemini 3.7 FlashHigh | Rank 7 | 16.57 | 28 of 30 |
| Gemini 3.8 FlashHigh | Rank 3 | 14.87 | 30 of 30 |
| Gemini 4 ArgonHigh | Rank 2 | 13.67 | 30 of 30 |
| GLM-5.3-FlashHigh | Rank 19 | 23.27 | 22 of 30 |
| GPT-5.6 LunaHigh | Rank 15 | 21.03 | 27 of 30 |
| GPT-5.6 SolHigh | Rank 12 | 18.07 | 29 of 30 |
| GPT-6 AstraHigh | Rank 1 | 13.67 | 30 of 30 |
| GPT-6 LunaHigh | Rank 16 | 21.17 | 24 of 30 |
| GPT-6 SolHigh | Rank 10 | 18.03 | 30 of 30 |
| GPT-6.1 SolHigh | Rank 6 | 15.23 | 29 of 30 |
| gpt-oss-120BHigh | Rank 18 | 22.23 | 20 of 30 |
| Grok 4.6High | Rank 8 | 17.13 | 30 of 30 |
| Grok 4.7High | Rank 17 | 22.23 | 22 of 30 |
| MiniMax M3High | Rank 20 | 29.17 | 15 of 30 |
| Muse Spark 1.3 ContributorHigh | Rank 13 | 18.37 | 29 of 30 |
| Muse WonderHigh | Rank 14 | 19.63 | 29 of 30 |
Lower question scores are better.