Compare Mistral Devstral Small 1.1 and Mistral Small 4, both from Mistral AI, tested across 53 shared challenges. Updated April 2026.
Mistral Devstral Small 1.1 and Mistral Small 4 are both competitive models. Mistral Devstral Small 1.1 costs $0.1/M input tokens vs $0.15/M for Mistral Small 4. Compare their real outputs side by side below.
Mistral Devstral Small 1.1 is made by mistral while Mistral Small 4 is from mistral. On pricing, Mistral Devstral Small 1.1 costs $0.1/M input tokens vs $0.15/M for Mistral Small 4.
No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.
Mistral Small 4 uses 19.0x more emoji
Ask them anything yourself
Some models write identically. You are paying for the brand.
178 models fingerprinted across 32 writing dimensions. Free research.
185x
price gap between models that write identically
178
models
12
clone pairs
32
dimensions
279 AI models invented the same fake scientist.
We read every word. 250 models. 2.14 million words. This is what we found.

Compare Mistral Devstral Small 1.1 and Mistral Small 4, both from Mistral AI, tested across 53 shared challenges. Updated April 2026.
Mistral Devstral Small 1.1 and Mistral Small 4 are both competitive models. Mistral Devstral Small 1.1 costs $0.1/M input tokens vs $0.15/M for Mistral Small 4. Compare their real outputs side by side below.
Mistral Devstral Small 1.1 is made by mistral while Mistral Small 4 is from mistral. On pricing, Mistral Devstral Small 1.1 costs $0.1/M input tokens vs $0.15/M for Mistral Small 4.
No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.
Mistral Small 4 uses 19.0x more emoji
Ask them anything yourself
Some models write identically. You are paying for the brand.
178 models fingerprinted across 32 writing dimensions. Free research.
185x
price gap between models that write identically
178
models
12
clone pairs
32
dimensions
279 AI models invented the same fake scientist.
We read every word. 250 models. 2.14 million words. This is what we found.
