跳轉到主要內容

Command A+

CohereCommand開源權重Apache 2.0 · 商用許可

描述

Command A+ is Cohere's open-source sparse Mixture-of-Experts model for enterprise agentic, multilingual, multimodal, and reasoning-heavy tasks. It has 218B total parameters with 25B active parameters, supports text and image inputs, conversational tool use, generated thinking, 48 languages, a 128K input context, and up to 64K output tokens.

發布日期
2026-05-20
參數規模
218.0B
上下文長度
256K
支援模態
text

能力雷達圖

20
general
29
coding
76
reasoning
50
science
80
agents
0
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜293
42.0
AA
通用能力榜174
60.0
AA
多模態榜70
45.0
LS
科學能力222
54.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Cohere Agentic Question Answering65.0%自報
Cohere Memory Usage Quality54.0%自報

Communication

Tau2 Telecom85.0%自報

Data Analysis

Cohere Data Analysis45.0%自報

Instruction Following

IFBench74.0%自報

Language

WMT24++81.0%自報

Math

AIME 202590.0%自報
MT-AIME 202586.0%自報
MathVista80.6%自報

Multimodal

MMMU75.1%自報

Reasoning

CharXiv-D88.0%自報
CharXiv-R52.7%自報
SciCode38.0%自報
Terminal-Bench Hard25.0%自報

Vision

MMMU-Pro63.0%自報

AA 評測指數

(Artificial Analysis)
Tau2(Sierra + U Toronto + Vector Institute (2025))
80.7
Gpqa(NYU + Cohere + Anthropic (2023))
76.1
Ifbench(Google Research (2023))
73.9
Lcr(Artificial Analysis)
48.7
Scicode(UIUC + Argonne National Lab (2024))
37.8
Coding Index(Artificial Analysis)
27.8
Terminalbench Hard(Stanford × Laude Institute (2026))
25.0
Terminalbench V2 1
22.8
Intelligence Index(Artificial Analysis)
22.8
Hle(Center for AI Safety + Scale AI (2025))
12.0
Tau Banking
6.0

LLM Stats 分類評分

(LLM Stats (zeroeval))
Structured Output
90
Language
80
Healthcare
80
Communication
80
Tool Calling
80
Math
70
Multimodal
70
Reasoning
70
Instruction Following
70
General
70
Vision
70
Physics
40
Biology
40
Chemistry
40
Code
40

定價

輸入價格免費
輸出價格免費
混合價格(3:1)免費

速度

Tokens/秒245.4
首Token延遲0.15s
首回答延遲8.30s

供應商價格排行

供應商價格排行

2 個供應商

最便宜: NanoGPT最貴: Cohere
供應商輸入輸出
1NanoGPT最便宜
$2.5
$10
2Cohere
$2.5
$10

比較該模型在不同 API 供應商之間的定價。

外部連結