token.app › Compare › Mistral Large vs Mistral Small 3
Mistral Large vs Mistral Small 3
Mistral Small 3 leads on 2 of 2 shared benchmarks. Mistral Small 3 is 52× cheaper per token on a blended 3:1 basis. Mistral Large accepts the larger context window (128K).
Head to head
Blended price uses a 3:1 input:output mix
| Mistral Large | Mistral Small 3 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Input $/1M | $2.00 | $0.050 |
| Output $/1M | $6.00 | $0.080 |
| Blended $/1M | $3.00 | $0.058 |
| Context window | 128K | 33K |
| Max output | — | 16K |
| Released | Feb 2024 | Jan 2025 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 38.8% | 45.3% |
| OTIS Mock AIME | 1.9% | 5.3% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Mistral Large if…
- Larger context window (128K)
Choose Mistral Small 3 if…
- Costs less per token — $0.058 vs $3.00 blended
- Higher GPQA Diamond (45.3% vs 38.8%)
- Higher OTIS Mock AIME (5.3% vs 1.9%)
- Open weights — self-hostable
- Newer model (released Jan 2025)
FAQ
Which is better, Mistral Large or Mistral Small 3?
Across the 2 benchmarks both models have independently-run scores for, Mistral Large leads on 0 and Mistral Small 3 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Mistral Large cheaper than Mistral Small 3?
Mistral Small 3 is cheaper: $0.058 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $2.00 vs $0.050. Output alone: $6.00 vs $0.080.
What context windows do Mistral Large and Mistral Small 3 have?
Mistral Large: 128,000 tokens. Mistral Small 3: 32,768 tokens.
Who makes Mistral Large and Mistral Small 3?
Mistral Large is made by Mistral AI. Mistral Small 3 is made by Mistral AI.