4 Deepcogito models evaluated
| Rank | Model | Accuracy | Correct | Total | Incorrect | Errors |
|---|---|---|---|---|---|---|
| 1 | Deepcogito/Cogito-V2-Preview-Deepseek-671b |
80.5 ± 10.2% | 31 | 38 | 5 | 2 |
| 2 | Deepcogito/Cogito-V2-Preview-Llama-70b |
71.9 ± 14.3% | 19 | 26 | 7 | 0 |
| 3 | Deepcogito/Cogito-V2-Preview-Llama-405b |
70.7 ± 28.0% | 1 | 1 | 0 | 0 |
| 4 | Deepcogito/Cogito-V2-Preview-Llama-109b-Moe |
68.5 ± 15.9% | 16 | 23 | 7 | 0 |