Ministral 3 3B 2512 vs Ministral 3 8B 2512

Mistral AI against Mistral AI, the same lab's consecutive models. Prices, scores and speed below are live.

  • Ministral 3 3B 2512 costs 33% less on blended price ($0.15 against $0.23 per 1M tokens, 3 input to 1 output).
  • Ministral 3 8B 2512 scores higher on the Artificial Analysis Intelligence Index: 5.5 against 4.8.
  • On the 7 benchmarks both have scores on, Ministral 3 3B 2512 leads on 1 and Ministral 3 8B 2512 on 6.
  • Ministral 3 8B 2512 reads more context: 262K tokens against 131K.
  • Ministral 3 8B 2512 is newer: listed Dec 2, 2025, against Dec 2, 2025.

Side by side

Ministral 3 3B 2512Ministral 3 8B 2512
LabMistral AIMistral AI
ListedDec 2, 2025Dec 2, 2025
Input per 1M tokens$0.15$0.23
Output per 1M tokens$0.15$0.23
Cached input per 1M$0.015$0.022
Blended (3:1) per 1M$0.15$0.23
Context window131K262K
Max output105K210K
Knowledge cutoff--
Intelligence index4.85.5
Coding index4.89.7
ReasoningNoNo
Reads imagesYesYes
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Mistral AI models, Mistral AI models, every LLM's price and our sources.