Command A+

Command A+.

Cohere Released 20 May 2026

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Cohere May 2026

Open weights

No Epoch Capabilities Index score yet

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Benchmark	Score	Rank	Source
IFBench	74%	#27 of 70	Model card
SEA-HELM	56.7	#52 of 62	Official leaderboard
WMT24++	81%	#11 of 12	Model card
MT-AIME (Cohere internal)	86%	#1 of 1	Model card

Benchmark	Score		Rank	Source
AIME 2025	90%		#50 of 143	Model card
CritPt	0.29%		#113 of 160	Epoch AI

Benchmark	Score		Rank	Source
SciCode	38%		#34 of 47	Model card

Benchmark	Score		Rank	Source
tau2-bench	85%		#25 of 69	Model card
Terminal-Bench Hard	25%		#7 of 11	Model card

Benchmark	Score	Rank	Source
LegalBench	61.4%	#129 of 138	Official leaderboard
MedScribe	55.7%	#94 of 98	Official leaderboard
MedCode	19.7%	#96 of 96	Official leaderboard
Vals Finance Agent v2	9.04%	#80 of 80	Official leaderboard

Benchmark	Score	Rank	Source
MathVista	80.6%	#25 of 64	Model card
MMMU	75.1%	#39 of 97	Model card
MMMU-Pro	63%	#52 of 72	Model card
CharXiv	52.7%	#62 of 67	Model card

Benchmark	Score		Rank	Source
Artificial Analysis Intelligence Index v4.0	37.0		#5 of 5	Model card

The benchmarks the lab chose to headline, with the scores it gave.