Command A vs Pixtral Large

Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.

Pixtral Large by Mistral wins on 11 of 14 benchmarks against Command A by Cohere, which leads on 2. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from our benchmark data.

Category-by-Category Breakdown

General Intelligence: In general intelligence, Pixtral Large scores 1270 on Chatbot Arena ELO compared to Command A's 1250, while Pixtral Large scores 70.0% on MMLU-Pro compared to Command A's 68.0%.

Coding: In coding, Pixtral Large scores 80.0% on HumanEval+ compared to Command A's 78.0%, while Pixtral Large scores 35.0% on SWE-bench Verified compared to Command A's 32.0%, while Pixtral Large scores 40.0% on LiveCodeBench compared to Command A's 35.0%.

Math: In math, Pixtral Large scores 74.0% on MATH compared to Command A's 72.0%, while Pixtral Large scores 90.0% on GSM8K compared to Command A's 88.0%.

Reasoning: In reasoning, Pixtral Large scores 48.0% on GPQA Diamond compared to Command A's 45.0%, while Pixtral Large scores 22.0% on ARC-AGI compared to Command A's 15.0%.

Context: In context, Command A scores 256K on Context Length compared to Pixtral Large's 131K.

Pricing Comparison

Command A costs $2.5/1M input tokens and $10.0/1M output tokens, while Pixtral Large costs $2.0/1M input and $6.0/1M output. Pixtral Large is the more affordable option for API usage.

Speed Comparison

Command A generates output at 70 tok/s compared to Pixtral Large's 60 tok/s, and the time to first token is 400 ms for Command A versus 400 ms for Pixtral Large. Command A delivers faster throughput.

Verdict

For developers prioritizing speed, Command A has the edge. For those who value coding and general intelligence and math and affordability, Pixtral Large is the stronger choice.

View Individual Model Pages

Command A vs Pixtral Large — FAQ

Which is better, Command A or Pixtral Large?

Pixtral Large wins on more benchmarks overall (11 vs 2). However, the best choice depends on your specific needs — each model excels in different areas.

How does Command A compare to Pixtral Large for coding?

Pixtral Large is better for coding, scoring 35.0% on SWE-bench Verified compared to 32.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.

Is Command A cheaper than Pixtral Large?

Yes, Pixtral Large is cheaper. Command A costs $2.5/1M input and $10.0/1M output tokens. Pixtral Large costs $2.0/1M input and $6.0/1M output tokens.

Which is faster, Command A or Pixtral Large?

Command A is faster, generating output at 70 tok/s compared to 60 tok/s. Faster output speed means shorter wait times for API responses.

What benchmarks does the Command A vs Pixtral Large comparison cover?

This comparison covers 14 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, MATH, GPQA Diamond, SWE-bench Verified, Output Speed, LiveCodeBench, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.