What is the best Cohere model?

Command A has the highest verification score of the Cohere models we tested: 45.0% (36 of 80 correct) in our 2026-10-27 run.

What is the fastest Cohere model?

Command A is the fastest Cohere model we tested, at a median 7 output tokens per second.

What is the cheapest Cohere model?

Command A has the lowest billed cost per question of the Cohere models we tested: $0.007.

Provider

Cohere AI models

1 model tested, compared with 77 models from other labs.

Best verification score45.0Command A · #49 of 78 Best output speed7Command A · #71 of 78 Best time to first token1.8 sCommand A · #61 of 78 Best cost per question$0.007Command A · #56 of 78

Cohere#49Command A45.0% verification score7 tok/s1.8 s first token$0.007 / question

Score vs. cost per question

Cohere models in color, every other model in grey

Output speed vs. cost per question

Cohere models in color, every other model in grey

Verification score

Cohere models highlighted against every model in this run · higher is better

61 more models · see the full leaderboard

Output speed

Cohere models highlighted against every model in this run · higher is better

61 more models · see the full leaderboard

Time to first token

Cohere models highlighted against every model in this run · lower is better

63 more models · see the full leaderboard

Cost per question

Cohere models highlighted against every model in this run · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
56Command A$0.007

61 more models · see the full leaderboard

End-to-end response time

Cohere models highlighted against every model in this run · lower is better

63 more models · see the full leaderboard

Context window

Cohere models highlighted against every model in this run · higher is better

67 more models · see the full leaderboard

All Cohere results

Leaderboard
#
1	Command A Cohere · served by Cohere	45.0	36 / 80	7	1.8 s	$0.007	$2.5 / $10	256k

Cohere: quick answers

What is the best Cohere model?: Command A has the highest verification score of the Cohere models we tested: 45.0% (36 of 80 correct) in our 2026-10-27 run.
What is the fastest Cohere model?: Command A is the fastest Cohere model we tested, at a median 7 output tokens per second.
What is the cheapest Cohere model?: Command A has the lowest billed cost per question of the Cohere models we tested: $0.007.
Which Cohere models do you test?: Command A.

Provider

Cohere AI models

1 model tested, compared with 77 models from other labs.

Best verification score45.0Command A · #49 of 78 Best output speed7Command A · #71 of 78 Best time to first token1.8 sCommand A · #61 of 78 Best cost per question$0.007Command A · #56 of 78

Cohere#49Command A45.0% verification score7 tok/s1.8 s first token$0.007 / question

Score vs. cost per question

Cohere models in color, every other model in grey

Output speed vs. cost per question

Cohere models in color, every other model in grey

Verification score

Cohere models highlighted against every model in this run · higher is better

61 more models · see the full leaderboard

Output speed

Cohere models highlighted against every model in this run · higher is better

61 more models · see the full leaderboard

Time to first token

Cohere models highlighted against every model in this run · lower is better

63 more models · see the full leaderboard

Cost per question

Cohere models highlighted against every model in this run · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
56Command A$0.007

61 more models · see the full leaderboard

End-to-end response time

Cohere models highlighted against every model in this run · lower is better

63 more models · see the full leaderboard

Context window

Cohere models highlighted against every model in this run · higher is better

67 more models · see the full leaderboard

All Cohere results

Leaderboard
#
1	Command A Cohere · served by Cohere	45.0	36 / 80	7	1.8 s	$0.007	$2.5 / $10	256k

Cohere: quick answers

What is the best Cohere model?: Command A has the highest verification score of the Cohere models we tested: 45.0% (36 of 80 correct) in our 2026-10-27 run.
What is the fastest Cohere model?: Command A is the fastest Cohere model we tested, at a median 7 output tokens per second.
What is the cheapest Cohere model?: Command A has the lowest billed cost per question of the Cohere models we tested: $0.007.
Which Cohere models do you test?: Command A.