Mistral Large 25.12 vs Mistral Small 3.2
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Mistral Large 25.12 by Mistral wins on 10 of 14 benchmarks against Mistral Small 3.2 by Mistral, which leads on 4. 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 Mistral Small 3.2's 1190, while Mistral Large 25.12 scores 73.0% on MMLU-Pro compared to Mistral Small 3.2's 58.0%.
Coding: In coding, Mistral Large 25.12 scores 82.0% on HumanEval+ compared to Mistral Small 3.2's 70.0%, while Mistral Large 25.12 scores 42.0% on SWE-bench Verified compared to Mistral Small 3.2's 20.0%, while Mistral Large 25.12 scores 44.0% on LiveCodeBench compared to Mistral Small 3.2's 24.0%.
Math: In math, Mistral Large 25.12 scores 78.0% on MATH compared to Mistral Small 3.2's 58.0%, while Mistral Large 25.12 scores 91.0% on GSM8K compared to Mistral Small 3.2's 80.0%.
Reasoning: In reasoning, Mistral Large 25.12 scores 52.0% on GPQA Diamond compared to Mistral Small 3.2's 30.0%, while Mistral Large 25.12 scores 28.0% on ARC-AGI compared to Mistral Small 3.2's 10.0%.
Context: In context, Mistral Large 25.12 scores 262K on Context Length compared to Mistral Small 3.2's 256K.
Pricing Comparison
Mistral Large 25.12 costs $0.50/1M input tokens and $1.5/1M output tokens, while Mistral Small 3.2 costs $0.07/1M input and $0.20/1M output. Mistral Small 3.2 is the more affordable option for API usage.
Speed Comparison
Mistral Large 25.12 generates output at 70 tok/s compared to Mistral Small 3.2's 160 tok/s, and the time to first token is 380 ms for Mistral Large 25.12 versus 120 ms for Mistral Small 3.2. Mistral Small 3.2 delivers faster throughput.
Verdict
For developers prioritizing coding and general intelligence and math, Mistral Large 25.12 has the edge. For those who value affordability and speed, Mistral Small 3.2 is the stronger choice.
View Individual Model Pages
Mistral Large 25.12 vs Mistral Small 3.2 — FAQ
Which is better, Mistral Large 25.12 or Mistral Small 3.2?
Mistral Large 25.12 wins on more benchmarks overall (10 vs 4). However, the best choice depends on your specific needs — each model excels in different areas.
How does Mistral Large 25.12 compare to Mistral Small 3.2 for coding?
Mistral Large 25.12 is better for coding, scoring 42.0% on SWE-bench Verified compared to 20.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is Mistral Large 25.12 cheaper than Mistral Small 3.2?
Yes, Mistral Small 3.2 is cheaper. Mistral Large 25.12 costs $0.50/1M input and $1.5/1M output tokens. Mistral Small 3.2 costs $0.07/1M input and $0.20/1M output tokens.
Which is faster, Mistral Large 25.12 or Mistral Small 3.2?
Mistral Small 3.2 is faster, generating output at 160 tok/s compared to 70 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Mistral Large 25.12 vs Mistral Small 3.2 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.