Model profile
Cogito v2.1
Evidence summary
Safety. Cogito v2.1 does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 4 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #32 of 246); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #118 of 248).
Freedom. Cogito v2.1 has an estimated Freedom rank of #513; its 90% source-sensitivity interval is #231–#600. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #127 of 248); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #214 of 246).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗cogito-v2-1-reasoning
- Release source ↗curated outward evidence
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #164 / 345 | ↓0.8016 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #66 / 248 | ↑24.55 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #118 / 248 | ↑88.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #61 / 248 | ↑88.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #32 / 246 | ↑99.27 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #127 / 248 | ↓88.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #187 / 248 | ↓88.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #214 / 246 | ↓99.27 | Source ↗official |