Verdict
Built from the measurements below
- Mistral Large 4 is more accurate: 50.0% against 32.5% on the same 80 questions, a 17.5-point gap that is statistically significant.
- Mistral Small 4 is 6.1× cheaper per question as billed ($0.0019 vs $0.011), reasoning tokens included.
- Mistral Small 4 generates text 2.0× faster: 170 tokens per second against 83.
- Mistral Small 4 starts answering sooner: 0.5 s to the first token, against 1.1 s for Mistral Large 4.
- Mistral Large 4 accepts more context: 1M tokens against 262k.
Which should you choose?
Choose Mistral Large 4 for the most accurate answers of the two and a 1M-token context window. Choose Mistral Small 4 for the lower cost per correct answer ($0.0057 against $0.023), faster streaming, a quicker first token and open weights you can run yourself. The widest subject gap is in science: Mistral Large 4 answered 20 of 30 correctly, Mistral Small 4 7 of 30. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.
Accuracy gap +17.5 points (z = 2.25). We call a winner only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.