Skip to content

Mistral Small 4 (Non-reasoning)

Available

Mistral · 2026-03-16 · 32,000 tokens

An AI model from Mistral, suited to a broad range of AI workloads.

Supported modalities:textcode

Quick Overview

Text Generation1/10
Code Generation6/10
Reasoning6/10
Multimodal1/10

Benchmark Results

Scores from leading benchmark suites.

artificial analysis intelligence12.3

Performance Metrics

Latency and throughput performance.

P50 Latency
147.129tokens/sec

Dive Deeper