Inference
EN
Cohere

Command A

Command A is a model from Cohere. 8 benchmarks count toward its index, in 4 categories.

  • Input: text
RankedEnough results for an index.
IndexAll categories, out of 100.23.9±9.2Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.1331±3 #230Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted25.3212 / 218
CodingCode writing and repair.2 counted12.7208 / 209
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.2 counted26.7251 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.2 counted23.0156 / 168

Results

8 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH 500Math76.2% ±1.944 / 59
AIMEMath13.3% ±0.985 / 95
MMLU ProKnowledge69.2% ±0.5122 / 135
GPQA Diamond · Vals AIKnowledge48.5% ±2.3122 / 135
LiveCodeBenchCoding35.1% ±1.1136 / 142
Terminal-Bench 1.0Agentic6.3% ±2.746 / 47
Terminal-Bench 2.0 · Vals AIAgentic2.2% ±1.665 / 66
SWE-benchCoding7.8% ±1.287 / 87
CaseLaw v2Legal64.5% ±1.113 / 53
LegalBenchLegal79.7% ±0.493 / 149
MedQAHealthcare80.5% ±0.472 / 95
TaxEval v2Finance61.4% ±1.0123 / 143
CorpFin v2Finance46.0% ±1.0114 / 131
MGSMMultilingual85.7% ±2.066 / 74
Finance Agent v1.1Finance4.2% ±1.048 / 51

Sources

BenchLMCC BY-NC 4.0Vals AINo licence stated

History

5 releases
Index24.7 → 23.9
23 Oct 202612 Nov 2026

Questions

How good is Command A?
Its index is 23.9 out of 100. That is place 273 of 283 ranked models.
What is Command A best at?
Math: 23.0 out of 100, place 156 of 168.

Badge

Command A on Inference360: place 273 of 283, index 23.9
HTML
<a href="https://inference360.ai/models/cohere-command-a"><img src="https://inference360.ai/badges/cohere-command-a.svg" alt="Command A on Inference360: place 273 of 283, index 23.9" height="20"></a>
Markdown
[![Command A on Inference360: place 273 of 283, index 23.9](https://inference360.ai/badges/cohere-command-a.svg)](https://inference360.ai/models/cohere-command-a)

Compare with

Claude 3.5 Haiku24.1Mistral Small 3.124.2

More from Cohere

All models
Command A+40.2North Mini Code38.0Command RUnrankedCommand R (08-2024)UnrankedCommand R PlusUnranked