Private AI
Nvidia's latest Llama fine-tune optimized for instruction following. Early results hints that it might outperform models such as GPT-4o and Claude 3.5 Sonnet.
Added Apr 15, 2025
Context Window
16.4K
Max Output
8.2K
Input Price (Auto)
$0.36/1M
Output Price (Auto)
$0.41/1M
Cache Read (Auto)
$0.18/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
7.6
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
46.5%
Better than 23% of models compared
HLE
Humanity's Last Exam
4.6%
Better than 25% of models compared
IFBench
Instruction-following benchmark
30.7%
Better than 15% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
23.1%
Better than 25% of models compared
AA-LCR
Long context reasoning evaluation
7.0%
Better than 20% of models compared
SciCode
Python programming for scientific computing
23.3%
Better than 27% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
4.5%
AIME 2025
American Invitational Mathematics Examination 2025
11.0%
Better than 15% of models compared
AIME
American Invitational Mathematics Examination
24.7%
Better than 52% of models compared
MMLU-Pro
Professional and academic subject knowledge
69.0%
Better than 33% of models compared
Last updated Jul 15, 2026
Artificial AnalysisBetter than 29% of models compared
LiveCodeBench
Contamination-free coding benchmark
16.9%
Better than 18% of models compared
Math-500
Diverse mathematical problem solving benchmark
73.3%
Better than 34% of models compared
