Advertise here
#436

Command A+

Cohere Release: 2026-09-23 Tested on: 2026-09-30 23:28 cohere/command-a-plus::low
218B total (25B active)MoEOpen source
(high) (medium) (low) (none)

Summary

Command A+ scores 3.0 on AI BENCHY and ranks #436. It has 3.5 reliability, a 1.5% pass rate, $0.073 total cost, and 92.50s average response time.

What makes Command A+ unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Model facts

Researched on 2026-09-23

Reported
Parameters
218B total (25B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0

Official model card reports counts and Apache-2.0 weights with runnable Transformers and vLLM instructions.

Parameter source Availability source

Score

3.0

Consistency

9.6

Reliability

3.5

Total Cost (Current Price)

$0.073

Total Output Tokens

25,521

Total Input Tokens

114,874

Input Price

$0.300 / 1M

Output Price

$1.500 / 1M

Cache Read Price

$0.150 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 23

Attempt pass rate: 1.5%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

92.50s

Response Time (max): 128.54s

Response Time (total): 2127.40s

API error: 22 Wrong answer: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#436 Command A+

low
Provider returned error
Cost
$0.000
Time
0.2s
Tokens
0 tok

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-10-01 18:33 $0.300 / 1M $1.500 / 1M $0.150 / 1M N/A

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Command A+lowvsCommand A+noneCommand A+lowvsSpan-02defaultCommand A+lowvsCommand A+highCommand A+lowvsd1-ultradefaultCommand A+lowvsXing4.0 29b A4bnoneFree AvailableCommand A+lowvsJev 1.13defaultCommand A+lowvsCommand A+mediumCommand A+lowvsDecider V1.2defaultCommand A+lowvsGrok 4.20noneCommand A+lowvsDecider V1.1 27Bdefault

Category Breakdown

Category Score Consistency Tests Correct
Agentic 2.8 1.6
Anti-AI Tricks 3.0 10.0
Coding 3.0 10.0
Combined 3.0 10.0
Data parsing and extraction 3.0 10.0
Domain specific 3.0 10.0
General Intelligence 3.0 10.0
Instructions following 3.0 10.0
Puzzle Solving 3.0 10.0
Tool Calling 3.0 10.0
Trivia 3.0 10.0

Compared models