Benchgen
Models/mistral-ai/

Mistral Small 3.1 24B Base

DraftPublic
Model CardTraining jobsEvaluations

Model Details

Mistral Small 3 1 24B Base

Quick answer: Mistral Small 3 1 24B Base is Mistral AI's Mar 2025 model scoring 56% MMLU-Pro. Apache 2.0. Mistral Small 3.1 24B pretrained base.

What Mistral Small 3 1 24B Base Is

Mistral Small 3 1 24B Base is Mistral AI's Mar 2025 release scoring 56% MMLU-Pro. Mistral Small 3.1 24B pretrained base.

Specifications

FieldValue
OrganizationMistral AI
LicenseApache 2.0
Release dateMar 2025
ModalityText only

Public Benchmark Scores

BenchmarkScoreSourceDate
MMLU-Pro56%Benchgen evaluationMar-2025

Pricing

Open weights — self-host at no cost.

Mistral Small 3 1 24B Base vs Alternatives

ModelMMLU-ProLicense
Mistral Small 3 1 24B Base56%Apache 2.0

Check the MMLU-Pro leaderboard for current comparisons.

Frequently Asked Questions

What is Mistral Small 3 1 24B Base? Mistral AI's Mar 2025 model scoring 56% MMLU-Pro. Apache 2.0.

Scores from Benchgen evaluations. Last updated 2026-07-24.