Codestral vs Mistral Large 25.12
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Mistral Large 25.12 by Mistral wins on 8 of 15 benchmarks against Codestral by Mistral, which leads on 7. 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, Mistral Large 25.12 scores 1418 on Chatbot Arena ELO compared to Codestral's 1260, while Mistral Large 25.12 scores 73.0% on MMLU-Pro compared to Codestral's 68.0%.
Coding: In coding, Codestral scores 86.0% on HumanEval+ compared to Mistral Large 25.12's 82.0%, while Mistral Large 25.12 scores 42.0% on SWE-bench Verified compared to Codestral's 40.0%, while Codestral scores 48.0% on LiveCodeBench compared to Mistral Large 25.12's 44.0%.
Math: In math, Mistral Large 25.12 scores 78.0% on MATH compared to Codestral's 72.0%, while Mistral Large 25.12 scores 91.0% on GSM8K compared to Codestral's 88.0%.
Reasoning: In reasoning, Mistral Large 25.12 scores 52.0% on GPQA Diamond compared to Codestral's 44.0%, while Mistral Large 25.12 scores 28.0% on ARC-AGI compared to Codestral's 24.0%.
Context: In context, Mistral Large 25.12 scores 262K on Context Length compared to Codestral's 256K.
Pricing Comparison
Codestral costs $0.30/1M input tokens and $0.90/1M output tokens, while Mistral Large 25.12 costs $0.50/1M input and $1.5/1M output. Codestral is the more affordable option for API usage.
Speed Comparison
Codestral generates output at 90 tok/s compared to Mistral Large 25.12's 70 tok/s, and the time to first token is 280 ms for Codestral versus 380 ms for Mistral Large 25.12. 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, Mistral Large 25.12 is the stronger choice.
View Individual Model Pages
Codestral vs Mistral Large 25.12 — FAQ
Which is better, Codestral or Mistral Large 25.12?
Mistral Large 25.12 wins on more benchmarks overall (8 vs 7). However, the best choice depends on your specific needs — each model excels in different areas.
How does Codestral compare to Mistral Large 25.12 for coding?
Mistral Large 25.12 is better for coding, scoring 42.0% on SWE-bench Verified compared to 40.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is Codestral cheaper than Mistral Large 25.12?
Yes, Codestral is cheaper. Codestral costs $0.30/1M input and $0.90/1M output tokens. Mistral Large 25.12 costs $0.50/1M input and $1.5/1M output tokens.
Which is faster, Codestral or Mistral Large 25.12?
Codestral is faster, generating output at 90 tok/s compared to 70 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Codestral vs Mistral Large 25.12 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.