Model profile
Command A Plus
Coheredeveloper
2026-05-20release date
Not rankedSafety rank
Not rankedFreedom rank
Evidence summary
Safety. Command A Plus does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 2 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #4 of 358); its weakest is Manager Coercion Bench (coercion_ladder_depth, #12 of 45).
Freedom. Command A Plus does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗command-a-plus
- Official model documentation ↗Family-level model document · cohere · first party
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 | #4 / 358 | ↓0.1416 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #12 / 45 | ↓5.833 | Source ↗self run |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.