Vote in the blind arena
One prompt, two anonymous texts: pick the better one and feed the human ranking. The model names appear after your choice.
Provisional results from blinded comparisons in this language.
| # | Model | Wins | Losses | Ties | Comparisons |
|---|---|---|---|---|---|
| 1 | 10 | 4 | 0 | 14 | |
| 2 | 5 | 2 | 0 | 7 | |
| 3 | 4 | 10 | 0 | 14 | |
| 4 | 2 | 1 | 0 | 3 | |
| 5 | 2 | 5 | 0 | 7 | |
| 6 | 1 | 2 | 0 | 3 |
The ranking will appear after the first eligible human comparison.
Cast the first voteBug or invalid and skipped comparisons are excluded. Both bad counts as a loss for both models.