Command A is an AI model by Cohere. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Massive Multitask Language Understanding professional benchmark
HuggingFace LeaderboardArtificial Analysis composite intelligence score across 10 sub-benchmarks
Artificial Analysis (via OpenRouter)Human preference ELO from blind head-to-head votes
LMSYS / HuggingFaceCoding Benchmarks
Artificial Analysis composite coding score
Artificial Analysis (via OpenRouter)Math Benchmarks
Reasoning Benchmarks
Artificial Analysis composite score for multi-step tool-using tasks
Artificial Analysis (via OpenRouter)Speed Benchmarks
Cost Benchmarks
Context Benchmarks
Available from 6 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 4 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Azure | $2.5 | $10 | — | 131K | Supported |
| Azure Cognitive Services | $2.5 | $10 | — | 131K | — |
| Cohere | $2.5 | $10 | — | 256K | Supported |
| Eden AI | $2.5 | $10 | — | 288K | — |
| OpenRouter | $2.5 | $10 | — | 256K | Supported |
| Vercel AI Gateway | $2.5 | $10 | — | 256K | Supported |
Command A — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare Command A With
Command A — Frequently Asked Questions
How intelligent is Command A?
Command A scores 1250 on the Chatbot Arena ELO rating, making it a mid-tier AI model. This score is based on blind head-to-head human preference voting.
How much does Command A cost?
Command A costs $2.5 per 1M input tokens and $10.0 per 1M output tokens. This is mid-range pricing for its capability level.
How fast is Command A?
Command A generates output at 70 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 400 ms.
How good is Command A at coding?
Command A achieves 32.0% on SWE-bench Verified, demonstrating moderate real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is Command A at math and reasoning?
Command A scores 72.0% on the MATH benchmark (competition-level mathematics). It also achieves 45.0% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of Command A?
Command A has a context window of 256K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Command A?
Command A was created by Cohere. It is classified as a flagship model in our catalogue.
Is Command A open source?
No, Command A is a proprietary model. It is available through Cohere's API and compatible providers.