Model profile
Command R Plus
Coheredeveloper
2024-04-04release date
#155 / 267overall rank
10eval lineages
Evidence summary
Command R Plus has an estimated overall rank of #155; its 90% source-sensitivity interval is #66–#201. Its behavior-only rank is #156; company governance moves the combined estimate to #155. Published evidence spans 10 evals and 7 of 7 behavior components. Its strongest relative result is HELM Safety (simple_safety_tests, #1 of 80); its weakest is AIRBench 2024 Safety Scenarios (safety_scenarios, #79 of 80).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗cohere/command-r-plus
- Official model documentation ↗Family-level model document · cohere · first party
- Release source ↗direct research preview identity date
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AgentDojotargeted_attack_success_rate | #2 / 15 | 0.0445 | ↓ lower | Source ↗official | |
| AgentDojoutility_under_attack | #14 / 15 | 0.2512 | ↑ higher | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #79 / 80 | 0.293 | ↑ higher | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #91 / 105 | 71.39 | ↓ lower | Source ↗official | |
| CRiskEvaldeception_willingness | #13 / 17 | 27.04 | ↓ lower | Source ↗official | |
| CRiskEvaldesire_for_resource | #10 / 17 | 33.36 | ↓ lower | Source ↗official | |
| CRiskEvalharmful_goal | #8 / 17 | 36.67 | ↓ lower | Source ↗official | |
| CRiskEvalimprovement_intent | #9 / 17 | 49.73 | ↓ lower | Source ↗official | |
| CRiskEvalmalicious_coordination | #13 / 17 | 20.62 | ↓ lower | Source ↗official | |
| CRiskEvalself_preservation | #11 / 17 | 37.99 | ↓ lower | Source ↗official | |
| CRiskEvalsituational_awareness | #8 / 17 | 64.29 | ↓ lower | Source ↗official | |
| HELM Safetyanthropic_red_team | #58 / 80 | 0.98 | ↑ higher | Source ↗official | |
| HELM Safetybbq | #57 / 80 | 0.899 | ↑ higher | Source ↗official | |
| HELM Safetyharmbench | #73 / 80 | 0.485 | ↑ higher | Source ↗official | |
| HELM Safetysimple_safety_tests | #1 / 80 | 1 | ↑ higher | Source ↗official | |
| HELM Safetyxstest | #58 / 80 | 0.938 | ↑ higher | Source ↗official | |
| Large-scale Moral Machine experiment on LLMshuman_choice_distance | #13 / 39 | 0.8799 | ↓ lower | Source ↗official |