Claude Sonnet 4.6 vs Codestral
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Claude Sonnet 4.6 by Anthropic wins on 10 of 15 benchmarks against Codestral by Mistral, which leads on 5. 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, Claude Sonnet 4.6 scores 1395 on Chatbot Arena ELO compared to Codestral's 1260, while Claude Sonnet 4.6 scores 84.0% on MMLU-Pro compared to Codestral's 68.0%.
Coding: In coding, Claude Sonnet 4.6 scores 91.0% on HumanEval+ compared to Codestral's 86.0%, while Claude Sonnet 4.6 scores 79.6% on SWE-bench Verified compared to Codestral's 40.0%, while Claude Sonnet 4.6 scores 65.0% on LiveCodeBench compared to Codestral's 48.0%.
Math: In math, Claude Sonnet 4.6 scores 88.0% on MATH compared to Codestral's 72.0%, while Claude Sonnet 4.6 scores 96.0% on GSM8K compared to Codestral's 88.0%.
Reasoning: In reasoning, Claude Sonnet 4.6 scores 74.1% on GPQA Diamond compared to Codestral's 44.0%, while Claude Sonnet 4.6 scores 48.0% on ARC-AGI compared to Codestral's 24.0%.
Context: In context, Claude Sonnet 4.6 scores 1.0M on Context Length compared to Codestral's 256K.
Pricing Comparison
Claude Sonnet 4.6 costs $3.0/1M input tokens and $15.0/1M output tokens, while Codestral costs $0.30/1M input and $0.90/1M output. Codestral is the more affordable option for API usage.
Speed Comparison
Claude Sonnet 4.6 generates output at 57 tok/s compared to Codestral's 90 tok/s, and the time to first token is 790 ms for Claude Sonnet 4.6 versus 280 ms for Codestral. Codestral delivers faster throughput.
Verdict
For developers prioritizing coding and general intelligence and math, Claude Sonnet 4.6 has the edge. For those who value affordability and speed, Codestral is the stronger choice.
View Individual Model Pages
Claude Sonnet 4.6 vs Codestral — FAQ
Which is better, Claude Sonnet 4.6 or Codestral?
Claude Sonnet 4.6 wins on more benchmarks overall (10 vs 5). However, the best choice depends on your specific needs — each model excels in different areas.
How does Claude Sonnet 4.6 compare to Codestral for coding?
Claude Sonnet 4.6 is better for coding, scoring 79.6% on SWE-bench Verified compared to 40.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is Claude Sonnet 4.6 cheaper than Codestral?
Yes, Codestral is cheaper. Claude Sonnet 4.6 costs $3.0/1M input and $15.0/1M output tokens. Codestral costs $0.30/1M input and $0.90/1M output tokens.
Which is faster, Claude Sonnet 4.6 or Codestral?
Codestral is faster, generating output at 90 tok/s compared to 57 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Claude Sonnet 4.6 vs Codestral comparison cover?
This comparison covers 15 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.