Real people, blind-ish card battles: one prompt, two models, pick the better answer. 3 votes so far. Start a battle with the ⚔ button in the chat.
| # | Model | Crowd Elo | W-L-T |
|---|---|---|---|
| 1 | GLM 5.3 Flash | 1012 | 1-0-0 |
| 2 | GLM 5.3 FlashX | 1012 | 1-0-0 |
| 3 | MiMo V2.5 | 1000 | 1-1-0 |
| 4 | Qwen 3.8 Max | 988 | 0-1-0 |
| 5 | DeepSeek V4.1 Flash | 988 | 0-1-0 |