Cohere

Command A benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place Command A, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.

Updated Oct 2, 2026Full leaderboard Sources and method

Read Oct 2, 2026

#39of 85

on the LLM leaderboard, with a consensus score of 50 across 2 leaderboards.

Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.

By leaderboard

Where each leaderboard places Command A

Artificial Analysis

#40of 51

Score 13.1. Best run: cohere/command-a.

Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.

LiveBench

Not measured by LiveBench.

Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.

LMArena

Not measured by LMArena.

Blind head-to-head human votes, style controlled.

Berkeley BFCL

#9of 37

Score 57.06%. Best run: Command A Reasoning (FC).

Function calling and tool use, single turn to multi turn and web search.

Price and context

$4.38

OpenRouter: $2.50 in, $10 out. Vercel AI Gateway: $2.50 in, $10 out Context window 256K tokens.

Nearby

The models either side of Command A

Questions about Command A

How good is Command A?

Command A ranks #39 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 50 out of 100 across 2 leaderboards.

Is Command A better than Inkling xHigh?

Not on the consensus: Inkling xHigh scores 51 to Command A's 50. Compare them source by source below, since the leaderboards test different things.

Is Command A better than Qwen3.5 397B A17B?

On the consensus, yes: 50 to 50.

How much does Command A cost?

$2.50 per million input tokens and $10 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $4.38 per million.

Is Command A good for coding?

It scores 27.8 on the Artificial Analysis Coding Index, placing it #40 for coding among the models on this leaderboard.

These models recommend brands. See if they name yours.

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
Who gets namedEvery competitor in the answers, most named first.
The pages AI readsThe sources behind each answer.
Three fixesWhat to fix first, with a brief for the first article.