---
title: "Command A 111B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Command A."
source: "https://rankedagi.com/models/command-a"
---

# Command A

| Field | Value |
| --- | --- |
| Organization | Cohere |
| License | Open Source |
| Size | 111B |
| Version | Latest |
| Released | 2025-03-13 |
| Context window | 256K |
| Input cost per million tokens | $2.5 |
| Output cost per million tokens | $10 |
| Model ID | command-a-03-2025 |
| Last updated | 2026-04-25T07:59:05.749Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 28.8% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 21.7% | RankedAGI Agentic Score |  |
| LiveCodeBench v6 | coding | 29.0% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| ChatArena (LMSYS) | coding | 1288 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| RankedAGI Reasoning | reasoning | 31.4% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 5.0% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 53.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1310 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 13.0% | AIME 2025 Competition Math |  |
| NYT Connections Extended | reasoning | 13.6% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| RankedAGI Math | math | 38.8% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 35.1% | Overall RankedAGI score |  |
| 𝜏²-Bench Telecom | Agents | 15.0% | Agentic Tool Use |  |
| GDPval-AA Elo | Agents | 283 | Office Tasks (Artificial Analysis) |  |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://cohere.com/blog/command-a |