GPT-5 Mini vs Mistral Large 25.12

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

GPT-5 Mini by OpenAI wins on 15 of 18 benchmarks against Mistral Large 25.12 by Mistral, which leads on 3. 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 GPT-5 Mini's 1300, while GPT-5 Mini scores 74.0% on MMLU-Pro compared to Mistral Large 25.12's 73.0%, while GPT-5 Mini scores 17.4 on AA Intelligence Index compared to Mistral Large 25.12's 9.7.

Coding: In coding, GPT-5 Mini scores 85.0% on HumanEval+ compared to Mistral Large 25.12's 82.0%, while GPT-5 Mini scores 48.0% on SWE-bench Verified compared to Mistral Large 25.12's 42.0%, while GPT-5 Mini scores 55.0% on LiveCodeBench compared to Mistral Large 25.12's 44.0%, while Mistral Large 25.12 scores 20.1 on AA Coding Index compared to GPT-5 Mini's 15.6.

Math: In math, GPT-5 Mini scores 82.0% on MATH compared to Mistral Large 25.12's 78.0%, while GPT-5 Mini scores 93.0% on GSM8K compared to Mistral Large 25.12's 91.0%.

Reasoning: In reasoning, GPT-5 Mini scores 55.0% on GPQA Diamond compared to Mistral Large 25.12's 52.0%, while GPT-5 Mini scores 30.0% on ARC-AGI compared to Mistral Large 25.12's 28.0%, while GPT-5 Mini scores 8.9 on AA Agentic Index compared to Mistral Large 25.12's 2.4.

Context: In context, GPT-5 Mini scores 400K on Context Length compared to Mistral Large 25.12's 262K.

Pricing Comparison

GPT-5 Mini costs $0.25/1M input tokens and $2.0/1M output tokens, while Mistral Large 25.12 costs $0.50/1M input and $1.5/1M output. GPT-5 Mini is the more affordable option for API usage.

Speed Comparison

GPT-5 Mini generates output at 180 tok/s compared to Mistral Large 25.12's 70 tok/s, and the time to first token is 150 ms for GPT-5 Mini versus 380 ms for Mistral Large 25.12. GPT-5 Mini delivers faster throughput.

Verdict

For developers prioritizing coding and math and affordability and speed, GPT-5 Mini has the edge. For those who value general intelligence, Mistral Large 25.12 is the stronger choice.

GPT-5 Mini vs Mistral Large 25.12 — FAQ

Which is better, GPT-5 Mini or Mistral Large 25.12?

GPT-5 Mini wins on more benchmarks overall (15 vs 3). However, the best choice depends on your specific needs — each model excels in different areas.

How does GPT-5 Mini compare to Mistral Large 25.12 for coding?

GPT-5 Mini is better for coding, scoring 48.0% on SWE-bench Verified compared to 42.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.

Is GPT-5 Mini cheaper than Mistral Large 25.12?

Yes, GPT-5 Mini is cheaper. GPT-5 Mini costs $0.25/1M input and $2.0/1M output tokens. Mistral Large 25.12 costs $0.50/1M input and $1.5/1M output tokens.

Which is faster, GPT-5 Mini or Mistral Large 25.12?

GPT-5 Mini is faster, generating output at 180 tok/s compared to 70 tok/s. Faster output speed means shorter wait times for API responses.

What benchmarks does the GPT-5 Mini vs Mistral Large 25.12 comparison cover?

This comparison covers 18 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.