Private AI
Mistral Small 4 is a hybrid MoE model that unifies instruct, reasoning, and coding behavior in a single multimodal model. It supports text and image input, native function calling, JSON output, and per-request reasoning effort controls.
Added Mar 16, 2026
Model weightsContext Window
262.1K
Max Output
16.4K
Avg output tokens (7d)
333 tokens
Input Price (Auto)
$0.40/1M
Output Price (Auto)
$1.40/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
12.4
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
16.4
Agentic Index
18.6
GPQA Diamond
Graduate-level scientific reasoning
57.1%
Better than 36% of models compared
HLE
Humanity's Last Exam
3.7%
Better than 7% of models compared
IFBench
Instruction-following benchmark
32.8%
Better than 21% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
18.4%
Better than 16% of models compared
AA-LCR
Long context reasoning evaluation
21.3%
Better than 34% of models compared
CritPt
Research-level physics reasoning
0.3%
Better than 58% of models compared
SciCode
Python programming for scientific computing
28.1%
Better than 39% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
10.6%
AA-Omniscience Accuracy
Proportion of correctly answered questions
16.3%
Better than 30% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
77.2%
Last updated Jun 17, 2026
Artificial AnalysisBetter than 44% of models compared
Better than 58% of models compared
