readable AI benchmarks

OpenAI

GPT-5.6 Sol (low)

reasoning · closed weights · Jul 9, 2026

Quality Score66.4
Value Score39.2
Reliability59.4
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
$0.231

Capability

Intelligence
50.7
Coding
69.7
Agentic
41.6
Omniscience
18.9
Correct
57.2%
Blended price
$4.35

Answer outcomes

Correct 57.2%Incorrect 38.3%Abstained 4.5%

Artificial Analysis benchmarks

GDPval-AA v2
47%
τ³-Banking
29%
Terminal-Bench v2.1
77%
SciCode
55%
Humanity’s Last Exam
39%
GPQA Diamond
90%
CritPt
15%
AA-Omniscience
59%
AA-LCR
73%

Similar models