Mistral Small (Sep '24)
MistralMistralOpen WeightApache 2.0 · Commercial OK
Description
Mistral Small 4 is Mistral AI's hybrid small model that unifies instruct, reasoning, multimodal understanding, and coding capabilities in a single efficient system. It uses a 119B-parameter Mixture-of-Experts architecture with native image input, a 256k context window, and configurable reasoning depth for general chat, coding agents, and long-context reasoning workloads.
Release Date
2024-09-17
Parameters
119.0B
Context Length
262K
Modalities
image, pdf, text
Capability Radar
70
general
60
coding
80
reasoning
60
scienceest.
74
agents
60
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Multimodal Ranking | 106 | 41.0 | LS |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
80.7%SR
TriviaQA
80.3%SR
Arena Hard
58.3%SR
Instruction Following
IFBench
48.0%SR
Language
MMLU-Pro
78.0%SR
COLLIE
62.9%SR
Math
AIME 2025
83.8%SR
GSM8k
80.7%SR
MATH
46.0%SR
Reasoning
ARC-C
91.3%SR
GPQANYU + Cohere + Anthropic (2023)
71.2%SR
AA-LCR
71.2%SR
MBPP
0.70 / 100SR
AGIEval
65.8%SR
LiveCodeBench
63.6%SR
Vision
MMMU-Pro
60.0%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Legal80
Math80
Finance80
Healthcare80
Language70
Long Context70
Physics70
Reasoning70
General70
Biology70
Chemistry70
Chat60
Multimodal60
Code60
Creativity60
Vision60
Writing60
Instruction Following50
Pricing
Input Price$0.15 / 1M tokens
Output Price$0.6 / 1M tokens
Blended Price (3:1)$0.2625 / 1M tokens
Cache Read Price$0.015 / 1M tokens
Speed
No speed data available
Provider Price Ranking
Provider Price Ranking
3 providers
Cheapest: HeliconeMost Expensive: Mistral AI
ProviderInputOutput
1HeliconeCheapest
$0.075
$0.2
2MistralPRIMARY
$0.15
$0.6
3Mistral AI
$0.15
$0.6
Compare pricing across different API providers for this model.