Codestral vs Grok 4
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Grok 4 by xAI wins on 9 of 14 benchmarks against Codestral by Mistral, which leads on 5. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from the AI Value Index.
Category-by-Category Breakdown
General Intelligence: In general intelligence, Grok 4 scores 1430 on Chatbot Arena ELO compared to Codestral's 1260, while Grok 4 scores 87.0% on MMLU-Pro compared to Codestral's 68.0%.
Coding: In coding, Grok 4 scores 90.0% on HumanEval+ compared to Codestral's 86.0%, while Grok 4 scores 72.0% on SWE-bench Verified compared to Codestral's 40.0%, while Grok 4 scores 65.0% on LiveCodeBench compared to Codestral's 48.0%.
Math: In math, Grok 4 scores 91.0% on MATH compared to Codestral's 72.0%, while Grok 4 scores 97.0% on GSM8K compared to Codestral's 88.0%.
Reasoning: In reasoning, Grok 4 scores 87.0% on GPQA Diamond compared to Codestral's 44.0%, while Grok 4 scores 50.0% on ARC-AGI compared to Codestral's 24.0%.
Context: In context, Codestral scores 262K on Context Length compared to Grok 4's 256K.
Pricing Comparison
Codestral costs $0.30/1M input tokens and $0.90/1M output tokens, while Grok 4 costs $3.0/1M input and $15.0/1M output. Codestral is the more affordable option for API usage.
Speed Comparison
Codestral generates output at 90 tok/s compared to Grok 4's 55 tok/s, and the time to first token is 280 ms for Codestral versus 500 ms for Grok 4. Codestral delivers faster throughput.
Verdict
For developers prioritizing affordability and speed, Codestral has the edge. For those who value coding and general intelligence and math, Grok 4 is the stronger choice.
View Individual Model Pages
Codestral vs Grok 4 — FAQ
Which is better, Codestral or Grok 4?
Grok 4 wins on more benchmarks overall (9 vs 5). However, the best choice depends on your specific needs — each model excels in different areas.
How does Codestral compare to Grok 4 for coding?
Grok 4 is better for coding, scoring 72.0% on SWE-bench Verified compared to 40.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is Codestral cheaper than Grok 4?
Yes, Codestral is cheaper. Codestral costs $0.30/1M input and $0.90/1M output tokens. Grok 4 costs $3.0/1M input and $15.0/1M output tokens.
Which is faster, Codestral or Grok 4?
Codestral is faster, generating output at 90 tok/s compared to 55 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Codestral vs Grok 4 comparison cover?
This comparison covers 14 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, MATH, SWE-bench Verified, GPQA Diamond, Output Speed, Time to First Token, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.