Mistral Small (Feb ’24)

Mistral Small (Feb ’24)

Mistral · Released Feb 26, 2024 Professional
Intelligence #10 / 576
82.0 Our Score
Speed #60 / 271
159.9 tokens / sec
Input #433 / 577
$1.00 per 1M tokens
Output #429 / 577
$3.00 per 1M tokens
Context
— Not reported

Analysis Summary

Mistral Small (Feb 2024) is an early compact model from Mistral, positioned as a cost-efficient option for straightforward language tasks. Its intelligence index places it well below current mid-tier models, and coding capability data is limited to a modest livecodebench score, making it unsuitable for technical or agentic workloads.

For businesses, it fits narrow use cases: simple content drafting, basic summarisation, or lightweight classification where cost is the primary constraint. Instruction-following and long-context reliability are not strengths at this tier, so it should not be used for client-facing or high-stakes outputs.

At $1/1M input tokens it is affordable, but newer Mistral releases and competing small models have since surpassed it on most benchmarks. Teams with a genuine need for a budget text model should evaluate more recent alternatives before committing to this version.

Assessed June 6, 2026

Editorial notes

Mistral Small (Feb 2024) is a lightweight, affordable model from Mistral with limited reasoning depth, suited to basic content drafting and low-complexity tasks at $1/1M input tokens.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence1.7Technical0Value6Content0
Intelligence 1.7/10
Technical 0/10
Content 0/10
Value 6/10

How Mistral Small (Feb ’24) compares

Mistral Small (Feb ’24) ranks #331 of 378 AI models we track for overall intelligence. At $1.00 per million input tokens it is cheaper than 25% of comparable models.

Performance Indices

Source: Artificial Analysis

9 Intelligence Index

Benchmark Scores

Intelligence

GPQA Diamond 30.2% Graduate-level scientific reasoning
HLE 4.4% Humanity's Last Exam
MMLU Pro 41.9% Multi-task language understanding
MATH 500 56.2% Mathematical problem-solving
AIME 0.7% Competition mathematics
SciCode 13.4% Scientific computing

Technical

LiveCodeBench 11.1% Live coding evaluation

Benchmark data from Artificial Analysis and Hugging Face

How does Mistral Small (Feb ’24) stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

ProviderMistral
Release Date February 26, 2024
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $1.00 $0.001000
Output $3.00 $0.003000

Leaderboard Categories

Frequently asked questions about Mistral Small (Feb ’24)

How much does Mistral Small (Feb ’24) cost?

Mistral Small (Feb ’24) costs $1.00 per million input tokens and $3.00 per million output tokens.

Who created Mistral Small (Feb ’24)?

Mistral Small (Feb ’24) is developed by Mistral and was released on February 26, 2024.