readable AI benchmarks

AI9Stars

G9v3-39A5B

reasoning · open weights · Aug 20, 2026

Quality Score39.5
Value Score37.1
Reliability51.9
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
131,072 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.0000
Output
$0.0000
Cached Input
not available
Cached Output
not available
Cost per task
$0.0000

Capability

Intelligence
34.0
Coding
33.1
Agentic
32.9
Omniscience
3.8
Correct
14.9%
Blended price
$0.0000

Answer outcomes

Correct 14.9%Incorrect 11.1%Abstained 74.0%

Artificial Analysis benchmarks

GDPval-AA v2
38%
τ³-Banking
22%
Terminal-Bench v2.1
33%
SciCode
34%
Humanity’s Last Exam
17%
GPQA Diamond
81%
CritPt
0%
AA-Omniscience
52%
AA-LCR
62%

Similar models