Private AI
Mistral Small 4 with reasoning enabled (reasoning_effort=high). A hybrid MoE model with deep step-by-step reasoning for complex prompts, coding, and multi-step problem solving.
Added Mar 17, 2026
Model weightsContext Window
262.1K
Max Output
16.4K
Avg output tokens (7d)
628 tokens
Input Price (Auto)
$0.40/1M
Output Price (Auto)
$1.40/1M
Cache Read (Auto)
$0.20/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
19.6
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
26.6
GPQA Diamond
Graduate-level scientific reasoning
76.9%
Better than 67% of models compared
HLE
Humanity's Last Exam
9.5%
Better than 60% of models compared
IFBench
Instruction-following benchmark
48.2%
Better than 57% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
41.2%
Better than 47% of models compared
AA-LCR
Long context reasoning evaluation
44.7%
Better than 55% of models compared
SciCode
Python programming for scientific computing
38.0%
Better than 66% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
17.4%
Last updated Jul 15, 2026
Artificial AnalysisBetter than 56% of models compared
