GPT-5.6 Luna (max)
OpenAIGPTProprietary
描述
GPT-5.6 Luna is the fastest and most cost-efficient tier of OpenAI's GPT-5.6 family, designed for cost-sensitive, high-volume workloads. It brings strong capability at OpenAI's lowest GPT-5.6 price, supports max reasoning effort, and has a 1.05M-token context window.
发布日期
2026-07-09
参数规模
—
上下文长度
1.1M
支持模态
image, pdf, text
能力雷达图
50
general
68
coding
91
reasoning
67
science
70
agents
85
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
Connectors
99.9%自报
Search and Function-Calling
89.7%自报
Capture-the-Flag Challenges (Internal)
85.2%自报
Toolathlon
53.4%自报
LifeSciBench
51.2%自报
Internal Research Debugging Evaluation
50.8%自报
Agents' Last Exam
50.3%自报
SEC-bench Pro
48.9%自报
RSI Index
41.9%自报
Big Finance Bench
36.0%自报
Management Consulting Tasks (Internal)
35.4%自报
PostTrainBench Lite
29.6%自报
KernelGen 1P
22.4%自报
AutomationBench
14.9%自报
ExploitGym
12.4%自报
GeneBench-Pro
10.8%自报
NanoGPT
1.7%自报
Code
BenchCAD (with Python tool)
73.9%自报
DeepSWE
67.2%自报
DeepSWE 1.1
67.0%
BenchCAD
63.1%自报
ExploitBench
33.2%自报
General
Artificial Analysis
51.0%
GDP.pdf
22.7%自报
Healthcare
HealthBench Consensus
95.1%自报
HealthBench
55.8%自报
HealthBench Professional
55.7%自报
HealthBench Hard
32.0%自报
Long Context
MRCR v2 (8-needle, 512K-1M)
41.3%自报
MRCR v2 (8-needle)
41.3%自报
Math
FrontierMath
78.6%自报
FrontierMath Tier 4 (v2)
58.5%自报
Multimodal
OSWorld 2.0
45.6%自报
Reasoning
GPQANYU + Cohere + Anthropic (2023)
92.3%自报
Terminal-Bench 2.1
84.7%自报
BrowseCompOpenAI (2025)
83.3%自报
Graphwalks BFS >128k
81.3%自报
SWE-Bench ProPrinceton NLP (2024)
62.7%自报
Graphwalks BFS 1M
51.2%自报
FrontierCode 1.1
39.8%
MedChemBench (Internal)
30.4%自报
ARC-AGI-3
0.2%自报
Vision
MMMU-Pro (with tools)
79.5%自报
MMMU-Pro
78.4%自报
AA 评测指数
(Artificial Analysis)Coding Index(Artificial Analysis)71.4
Intelligence Index(Artificial Analysis)52.3
Gpqa(NYU + Cohere + Anthropic (2023))0.9
Terminalbench V2 10.8
Lcr(Artificial Analysis)0.8
Scicode(UIUC + Argonne National Lab (2024))0.5
Hle(Center for AI Safety + Scale AI (2025))0.4
Tau Banking0.3
LLM Stats 分类评分
(LLM Stats (zeroeval))Physics90
Biology90
Chemistry90
Search80
Math70
Spatial Reasoning70
Tool Calling70
Multimodal60
Vision60
Long Context50
Reasoning50
General50
Healthcare50
Agents50
Code50
Safety40
Finance40
Science30
Systems20
定价
输入价格$0.2 / 1M tokens
输出价格$1.2 / 1M tokens
混合价格(3:1)$0.45 / 1M tokens
缓存读取价格$0.02 / 1M tokens
缓存写入价格$0.25 / 1M tokens
速度
Tokens/秒132.4
首Token延迟86.96s
首回答延迟86.96s
供应商价格排行
供应商价格排行
2 个供应商
最便宜: OpenAI最贵: Neon
供应商输入输出
1OpenAI最便宜
$0
$0
2Neon
$1
$6
比较该模型在不同 API 供应商之间的定价。