Deep Cogito
3 models 3 model cards read
What its model cards measure
Tall ticks are Deep Cogito model cards that list the benchmark in their headline table. Gray dots are cards that leave it out. Rows are the benchmarks the lab listed most, at least twice each, in the order it started using them.
Model cards
| Date | Model | Document | Benchmarks |
|---|---|---|---|
| 19 Nov 2025 | | Cogito v2.1 (Deep Cogito research blog) | 8 |
| 31 Jul 2025 | | Cogito v2 Preview (Deep Cogito research blog) | 8 |
| 8 Apr 2025 | | Cogito v1 Preview (Deep Cogito research blog) | 7 |
Every Deep Cogito model
-
Cogito v2.1 Nov 2025
-
Cogito v2 Preview 671B MoE Jul 2025
-
Cogito v1 Preview 70B Apr 2025