readable AI benchmarks

OpenAI

GPT-5.6 Luna (xhigh)

reasoning · closed weights · Jul 9, 2026

Quality Score55.6
Value Score51.3
Reliability44.6
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
$0.032

Capability

Intelligence
50.1
Coding
68.6
Agentic
44.4
Omniscience
-10.8
Correct
42.4%
Blended price
$0.174

Answer outcomes

Correct 42.4%Incorrect 53.2%Abstained 4.3%

Artificial Analysis benchmarks

GDPval-AA v2
51%
τ³-Banking
29%
Terminal-Bench v2.1
78%
SciCode
50%
Humanity’s Last Exam
37%
GPQA Diamond
89%
CritPt
21%
AA-Omniscience
45%
AA-LCR
73%

Similar models