Mistral: Mistral Small Creative

Mistral: Mistral Small Creative

mistralai · Released Dec 16, 2025 Efficient
Intelligence #273 / 556
31.1 Our Score
Speed #53 / 257
154.9 tokens / sec
Input #189 / 557
$0.100 per 1M tokens
Output #200 / 557
$0.300 per 1M tokens
Context #377 / 557
32,768 tokens

Analysis Summary

Mistral: Mistral Small Creative sits in the Efficient tier on our leaderboard, ranked #273 of 556 published models on overall intelligence. At $0.100 input and $0.300 output per 1M tokens, it is among the most expensive on the market. It offers a mid-sized context window and supports tool use and function calling.

Editorial notes

Mistral Small Creative is a low-cost, lightweight model with tool use support, but its intelligence index of 10.2 and weak coding benchmarks make it unsuitable for demanding business workflows.

Assessed May 14, 2026

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

Performance Profile

Intelligence2.3Technical0Value7.5Content3.5
Intelligence 2.3/10
Technical 0/10
Content 3.5/10
Value 7.5/10

Mistral Small Creative is an experimental small model designed for creative writing, narrative generation, roleplay and character-driven dialogue, general-purpose instruction following, and conversational agents.

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

10.2 Intelligence Index

Benchmark Scores

Intelligence

GPQA Diamond 38.1% Graduate-level scientific reasoning
HLE 4.3% Humanity's Last Exam
MMLU Pro 52.9% Multi-task language understanding
MATH 500 56.3% Mathematical problem-solving
AIME 6.3% Competition mathematics
SciCode 15.6% Scientific computing

Technical

LiveCodeBench 14.1% Live coding evaluation

Benchmark data from Artificial Analysis and Hugging Face

How does Mistral: Mistral Small Creative stack up?

Compare side-by-side with other efficient models.

Compare Models

Model Information

OpenRouter ID mistralai/mistral-small-creative
Providermistralai
Model FamilyMistral
Release Date December 16, 2025
Context Length32,768 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.10 $0.000100
Output $0.30 $0.000300

Leaderboard Categories