readable AI benchmarks

OpenAI

GPT-5.6 Sol (medium)

reasoning · closed weights · Jul 9, 2026

Quality Score70.1
Value Score42.0
Reliability59.7
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
$0.372

Capability

Intelligence
55.6
Coding
76.3
Agentic
47.9
Omniscience
19.4
Correct
57.8%
Blended price
$4.35

Answer outcomes

Correct 57.8%Incorrect 38.4%Abstained 3.9%

Artificial Analysis benchmarks

GDPval-AA v2
53%
τ³-Banking
36%
Terminal-Bench v2.1
86%
SciCode
56%
Humanity’s Last Exam
42%
GPQA Diamond
93%
CritPt
23%
AA-Omniscience
60%
AA-LCR
74%

Similar models