readable AI benchmarks

OpenAI

GPT-5.6 Sol (xhigh)

reasoning · closed weights · Jul 9, 2026

Quality Score73.0
Value Score44.1
Reliability60.5
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text, image
Output modalities
text
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$5.00
Output
$30.00
Cached Input
$0.500
Cached Output
$6.25
Cost per task
$0.807

Capability

Intelligence
59.0
Coding
78.3
Agentic
53.6
Omniscience
21.0
Correct
58.8%
Blended price
$4.35

Answer outcomes

Correct 58.8%Incorrect 37.8%Abstained 3.3%

Artificial Analysis benchmarks

GDPval-AA v2
59%
τ³-Banking
38%
Terminal-Bench v2.1
90%
SciCode
56%
Humanity’s Last Exam
47%
GPQA Diamond
93%
CritPt
29%
AA-Omniscience
60%
AA-LCR
76%

Similar models