Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
GPT-5.6 Luna
Closed
Share
Add to comparison
Tool use · Reasoning
Overview
Pricing
Evaluations
Evaluation overview
Overall rank
#18
84.8 points · 180 models
Coding rank
#11
89.2 points · 160 models
Data coverage
40 items
1 source · updated through 2026-07-09
Domain performance
Coding
#11 / 160
89.2
Research
#30 / 174
89.5
Agents
#15 / 125
86.4
Vision
#20 / 65
84.5
Long context
#9 / 82
88
Evaluation highlights
All evaluations
GPQA-Diamond
Reasoning · OpenAI GPT-5.6 Release
92.3%
17
/ 126
SWE-bench Pro
Coding · OpenAI GPT-5.6 Release
62.7%
9
/ 46
Toolathlon
Agents · OpenAI GPT-5.6 Release
53.4%
7
/ 26
BenchCAD
Multimodal · OpenAI GPT-5.6 Release
63.1%
2
/ 7
Graphwalks BFS 256k F1
Long context · OpenAI GPT-5.6 Release
81.3%
5
/ 9
SEC-Bench Pro
Cybersecurity · OpenAI GPT-5.6 Release
48.9%
3
/ 4
Basic information
Context (input / output)
1M / -
Release date
2026-07
Input modalities
Text · Image
Output modalities
Text
Release date
2026-07-09
Availability
OpenAI
Full pricing
Input
$1 /1M
Output
$6 /1M
Related links
Official site
Version relationships
GPT-5.6 family
GPT-5.6 Luna
Current
2026-07 · Current model
GPT-5.6 Sol
2026-07 · Same series
GPT-5.6 Terra
2026-07 · Same series