readable AI benchmarks

Cohere

Command A+

reasoning · open weights · May 20, 2026

Quality Score25.0
Value Score24.4
Reliability48.0
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text, image
Output modalities
text
Context window
192k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.0000
Output
$0.0000
Cached Input
not available
Cached Output
not available
Cost per task
$0.0000

Capability

Intelligence
22.8
Coding
27.8
Agentic
9.2
Omniscience
-4.0
Correct
8.9%
Blended price
$0.0000

Answer outcomes

Correct 8.9%Incorrect 12.9%Abstained 78.2%

Artificial Analysis benchmarks

GDPval-AA v2
11%
τ³-Banking
6%
Terminal-Bench v2.1
23%
SciCode
38%
Humanity’s Last Exam
12%
GPQA Diamond
76%
CritPt
0%
AA-Omniscience
48%
AA-LCR
49%

Similar models