readable AI benchmarks

Upstage

Solar Pro 3

reasoning · closed weights · Apr 6, 2026

Quality Score14.3
Value Score17.0
Reliability23.3
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
128k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.150
Output
$0.600
Cached Input
$0.015
Cached Output
not available
Cost per task
$0.146

Capability

Intelligence
14.5
Coding
16.2
Agentic
2.9
Omniscience
-53.4
Correct
18.5%
Blended price
$0.100

Answer outcomes

Correct 18.5%Incorrect 71.9%Abstained 9.6%

Artificial Analysis benchmarks

GDPval-AA v2
0%
τ³-Banking
9%
Terminal-Bench v2.1
12%
SciCode
25%
Humanity’s Last Exam
10%
GPQA Diamond
72%
CritPt
0%
AA-Omniscience
23%
AA-LCR
31%

Similar models