readable AI benchmarks

OpenAI

GPT-5.6 Sol (high)

reasoning · closed weights · Jul 9, 2026

Quality Score71.5
Value Score43.1
Reliability60.2
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
$0.548

Capability

Intelligence
57.3
Coding
77.2
Agentic
50.6
Omniscience
20.4
Correct
58.4%
Blended price
$4.35

Answer outcomes

Correct 58.4%Incorrect 38.0%Abstained 3.7%

Artificial Analysis benchmarks

GDPval-AA v2
56%
τ³-Banking
37%
Terminal-Bench v2.1
87%
SciCode
57%
Humanity’s Last Exam
46%
GPQA Diamond
93%
CritPt
26%
AA-Omniscience
60%
AA-LCR
75%

Similar models