Private AI
35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents
Context Window
128.0K
Max Output
4.1K
Input Price (Auto)
$0.48/1M
Output Price (Auto)
$1.43/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
7.4
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Agentic Index
5.1
GPQA Diamond
Graduate-level scientific reasoning
28.4%
Better than 5% of models compared
HLE
Humanity's Last Exam
4.8%
Better than 31% of models compared
GDPval-AA
Economically valuable tasks
0.0%
Better than 11% of models compared
CritPt
Research-level physics reasoning
0.0%
Better than 27% of models compared
SciCode
Python programming for scientific computing
6.3%
Better than 6% of models compared
LiveCodeBench
Contamination-free coding benchmark
4.8%
AIME
American Invitational Mathematics Examination
0.7%
Better than 9% of models compared
Math-500
Diverse mathematical problem solving benchmark
16.4%
Better than 1% of models compared
MMLU-Pro
Professional and academic subject knowledge
33.8%
Better than 4% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
15.7%
Better than 24% of models compared
Last updated Jun 4, 2026
Artificial AnalysisBetter than 3% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
76.2%
Better than 59% of models compared
