Private AI
Upstage's Solar Pro 3 is a Mixture-of-Experts (MoE) language model with 102B total parameters and 12B active parameters per forward pass, optimized for Korean with strong English and Japanese support.
Added Mar 3, 2026
Context Window
128.0K
Max Output
128.0K
Input Price (Auto)
$0.15/1M
Output Price (Auto)
$0.60/1M
Cache Read (Auto)
$0.015/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
14.1
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
16.2
GPQA Diamond
Graduate-level scientific reasoning
72.4%
Better than 56% of models compared
HLE
Humanity's Last Exam
10.1%
Better than 61% of models compared
IFBench
Instruction-following benchmark
71.2%
Better than 87% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
86.3%
Better than 79% of models compared
AA-LCR
Long context reasoning evaluation
27.0%
Better than 38% of models compared
SciCode
Python programming for scientific computing
24.7%
Better than 29% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
7.6%
Last updated Aug 4, 2026
Artificial AnalysisBetter than 40% of models compared