readable AI benchmarks (simplified)

readable AI benchmarks

Upstage

Solar Pro 3

reasoning · closed weights · Apr 6, 2026

Solar Pro 3 has a Quality Score of 17.7, ranking 453rd among 571 scored models. Per 1M tokens, pricing is $0.150 input, $0.600 output, and $0.015 cached input. It accepts text input, outputs text, and has a 128k token context window. Its Reliability Score is 23.3, ranking 428th among 573 scored models, below average (total average: 36.5). Its Value Score is 15.8, low compared with the total Value average of 31.4.

Quality Score17.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score15.8
Factual 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
Cache write
not available
Cost per task
$0.079

Capability

Intelligence
7.8
Coding
not available
Agentic
not available
Omniscience
-53.4
Correct
18.5%
Blended price
$0.100

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 90.4%

Correct 18.5%Incorrect 71.9%Partial / not attempted 9.6%

Artificial Analysis benchmarks

GDPval-AA v2
0%
τ³-Banking
9%
SciCode
25%
Humanity’s Last Exam
10%
GPQA Diamond
72%
CritPt
0%
AA-Omniscience
23%
AA-LCR
32%

Similar models

Support me! Patreon