Cohere Models: Intelligence, Performance & Price
Artificial Analysis has benchmarked 6 models from Cohere. Below is a comparison of the key metrics across these models.
- For intelligence, the top model from Cohere is Command A+ at 6.
- For speed, North Mini Code at 3.0 min has the lowest time per task.
- For latency, Tiny Aya Global at 0.18s offers the lowest time to first answer token.
- For pricing, Command A+ at $0.00 and North Mini Code at $0.00 offer the lowest cost per task.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Task
Cost
Cost per Intelligence Index Task
Performance
Time per Intelligence Index Task
Capability Scores
Capability Indexes
Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better
Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better
Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Briefcase v1.1 · Higher is better
Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better
All Cohere Releases
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Command A+ | 6 | 218B 25B active at inference time | 192k | $0.00 | 3.4 | 172 | |||
| North Mini Code | 3 | 30B 3B active at inference time | 256k | $0.00 | 3.0 | 167 | |||
| Command A | - | 111B | 256k | $3.25 | - | 66 | |||
| Command-R+ (Apr '24) | - | 104B | 128k | - | - | - | - | ||
| Tiny Aya Global | - | 3.4B | 8k | $0.00 | - | 131 | |||
| Command-R (Mar '24) | - | 35B | 128k | - | - | - | - |