Model dossier模型档案
GPT-5.6 Luna
GPT-5.6 Luna is a high-tier model from OpenAI (Intelligence Score 83.3/100). Strongest in math (94.5) and coding (91.9); best fit: quantitative and scientific work. It trails in preference (38.2). Budget-priced: $0.200 in / $1.20 out per 1M tokens. Context window 1.1M tokens — long-document friendly.
GPT-5.6 Luna 是 OpenAI 的高水平梯队模型(智能评分 83.3/100)。 最强项是数学(94.5分),其次是代码(91.9分);适合数理与科研任务。 短板是偏好(38.2分)。 定价属低价档:每百万 token 输入 $0.200 / 输出 $1.20。 上下文 1.1M token,长文档友好。
83.3
Intelligence Score · benchmark coverage 智能评分 · benchmark 覆盖 68%
◈
Benchmark scoresBenchmark 成绩
7 entries 条| Benchmark基准 | Score成绩 | Index指数 | Dated日期 | Measured by测评方 | |
|---|---|---|---|---|---|
| Humanity's Last ExamReasoning | 37.2 | 65 | — | 3rd-party第三方 | source ↗×3 |
| GPQA DiamondReasoning | 91.1⚡max | 95 | — | 3rd-party第三方 | source ↗×3 |
| SWE-bench VerifiedCoding | 93 | 97 | — | vendor-reported厂商自报 | source ↗ |
| AIME 2025Math | 100 | 100 | — | 3rd-party第三方 | source ↗×5 |
| ↳ ⚡medium | 81.2 | — | — | 3rd-party第三方 | source ↗ |
| FrontierMathMath | 78.6 | 88 | — | 3rd-party第三方 | source ↗×2 |
| Terminal-BenchCoding | 75.7 | 82 | — | official官方榜 | source ↗×6⚠±9 |
| LMArena (Chatbot Arena)Preference | 1452 | 38 | — | official官方榜 | source ↗ |
≡
Specs & pricing规格与价格
| Provider厂商 | OpenAI |
|---|---|
| Released发布 | 2026-07-09 |
| Context window上下文 | 1.1M tokens |
| Max output最大输出 | 128K tokens |
| Modality模态 | text+image+file->text |
| Reasoning tiers推理档位 | ⚡none ⚡low ⚡medium ⚡high ⚡max default默认 high · none / minimal / low / medium / high / xhigh |
| API input price输入价格 | $0.200 / 1M tokens |
| API output price输出价格 | $1.20 / 1M tokens |
⛓
Tools using this model使用它的工具
⚔
Head-to-head正面对比
How we score →评分方法 → · Catalog & pricing via the official OpenRouter API.模型目录与价格来自 OpenRouter 官方 API。