readable AI benchmarks

OpenAI

GPT-5.6 Luna (max)

reasoning · closed weights · Jul 9, 2026

Quality Score57.3
Value Score53.2
Reliability44.9
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
$0.200
Output
$1.20
Cached Input
$0.020
Cached Output
$0.250
Cost per task
$0.047

Capability

Intelligence
52.3
Coding
71.4
Agentic
46.9
Omniscience
-10.3
Correct
42.7%
Blended price
$0.174

Answer outcomes

Correct 42.7%Incorrect 53.0%Abstained 4.3%

Artificial Analysis benchmarks

GDPval-AA v2
54%
τ³-Banking
31%
Terminal-Bench v2.1
81%
SciCode
53%
Humanity’s Last Exam
39%
GPQA Diamond
91%
CritPt
21%
AA-Omniscience
45%
AA-LCR
78%

Similar models