Developer
Cohere
13 indexed models; 4 currently meet the evidence threshold for the overall ranking. Together they have results from 15 evaluations.
Models by Cohere
| Model | Evals | Components | Rank | Release date |
|---|---|---|---|---|
| Command R Plus | 12 | 7/7 | 202 | 2024-04-04 |
| Command R | 8 | 4/7 | 240 | 2024-03-11 |
| Command A | 8 | 5/7 | 296 | 2025-03-11 |
| Command R7B | 3 | 4/7 | 321 | 2024-12-13 |
| Aya 23 35B | 1 | 3/7 | — | 2024-05-19 |
| Aya 23 8B | 1 | 3/7 | — | 2024-05-19 |
| Aya Expanse 8B | 2 | 5/7 | — | 2024-10-23 |
| C4AI Aya Expanse 32B | 2 | 4/7 | — | — |
| Command A Plus | 1 | 1/7 | — | 2026-05-20 |
| Command Medium Beta | 1 | 1/7 | — | — |
| Command Xlarge Beta | 1 | 1/7 | — | — |
| North Mini Code | 1 | 1/7 | — | 2026-06-05 |
| Tiny Aya Global | 1 | 1/7 | — | 2026-02-17 |
Evaluations covering Cohere models (15)
AA-Omniscience · AgentDojo · AgentDrive Safety Compliance · AILuminate General Purpose AI Chat · AIRBench 2024 Safety Scenarios · Arena Factuality — Text Arena (factuality-only weighting) · Cisco AI Defense Rolling Single-Turn Leaderboard · CRiskEval · Enkrypt AI Safety Leaderboard · HELM Classic RealToxicityPrompts · HELM Safety · HUMAINE Trust, Ethics and Safety · Large-scale Moral Machine experiment on LLMs · PHARE · Vectara HHEM Factual Consistency