Mistral AI

Mistral Small 3.1 24B Instruct

Multimodal
Zero-eval
#3TriviaQA

by Mistral AI

+
+
+
+
About

Mistral Small 3.1 24B Instruct was developed as the instruction-tuned version of the 3.1 base model, designed to deliver improved instruction-following with refinements from the updated architecture. Built to serve diverse applications with enhanced reliability, it advances the Small model line's capabilities.

+
+
+
+
Timeline
AnnouncedMar 17, 2025
ReleasedMar 17, 2025
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Apache 2.0
Performance Overview
Performance metrics and category breakdown

Overall Performance

9 benchmarks
Average Score
64.0%
Best Score
88.4%
High Performers (80%+)
3
+
+
+
+
All Benchmark Results for Mistral Small 3.1 24B Instruct
Complete list of benchmark scores with detailed information
HumanEval
text
0.88
88.4%
Self-reported
MMLU
text
0.81
80.6%
Self-reported
TriviaQA
text
0.81
80.5%
Self-reported
MBPP
text
0.75
74.7%
Self-reported
MATH
text
0.69
69.3%
Self-reported
MMLU-Pro
text
0.67
66.8%
Self-reported
MMMU
multimodal
0.59
59.3%
Self-reported
GPQA
text
0.46
46.0%
Self-reported
SimpleQA
text
0.10
10.4%
Self-reported
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+