Mistral AI

Mistral Small 3.1

A compact multimodal model aimed at low-latency assistants and local deployment. Its Apache license and moderate size make it unusually practical for customization.

open-weightsvisionefficientmultilingual

Model record

Mistral Small 3.1 model overview

Mistral Small 3.1 is a open weights model from Mistral AI. It was released on March 17, 2025. Its strongest case is apache-licensed weights, while buyers should account for trails frontier models on complex reasoning.

Mistral Small 3.1 benchmark snapshot

EvaluationReported scoreWhat it probes
MMLU-Pro66.8Broad knowledge and multi-step reasoning
GPQA Diamond46.8Graduate-level science reasoning
SWE-bench VerifiedNot reportedVerified real-repository issue resolution
LiveCodeBench32.1Contamination-aware competitive programming
SWE-Bench ProNot reportedLonger, harder professional software tasks
Artificial Analysis Intelligence IndexNot reportedComposite third-party capability index; version matters

Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.

Mistral Small 3.1 strengths

  • Apache-licensed weights
  • Fits on a single high-memory GPU when quantized
  • Low serving cost

Mistral Small 3.1 limitations

  • Trails frontier models on complex reasoning
  • Smaller ecosystem than Llama
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.

Compare Mistral Small 3.1

Source record

Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.

Read Mistral AI announcement