Lineage
- Company
OpenAI- GPT Luna family
- GPT-5.6 LunaGPT-6 Lunathe family
- Assistants that offer it
- ChatGPTdefault, Free, Go (official page ↗)
- API price
- not recorded
Links read on 10/11/2026 on company pages, the press as a fallback; a link given for a family applies only to its latest version.
Rank in each benchmark
- General intelligenceEpoch AI, ECI index156.8154.9 to 158.831st out of 71
- User preferenceLMArena, Elo score145342nd out of 68
- Agent tasksEpoch AI, APEX-Agents43.0 %32.4 to 53.642nd out of 52
- Coding tasksEpoch AI, CursorBench35.9 %17th out of 18
- Code repairEpoch AI, DeepSWE67.2 %10th out of 26
Each segment of the bar is worth a tenth of the ranking; the 1st groups the best ranked. Rank among models released in 2026 and measured by the benchmark. Sources: Epoch AI, "Capabilities & benchmarking" (CC BY 4.0); LMArena, text with style control (CC BY 4.0); data as of 10 November 2026.
Effort settings
| Setting | Electricity use of a task | Tasks completed | Tokens per task |
|---|---|---|---|
| CursorBench, coding tasks | |||
| low | not estimated | 16.0 % | 3,288 |
| medium | not estimated | 22.2 % | 7,642 |
| high | not estimated | 29.4 % | 23,368 |
| xhigh | not estimated | 33.0 % | 40,598 |
| max | not estimated | 35.9 % | 87,284 |
| DeepSWE, code repair | |||
| low | not estimated | 1.6 % | 3,128 |
| medium | not estimated | 11.3 % | 8,180 |
| high | not estimated | 44.2 % | 25,778 |
| xhigh | not estimated | 56.9 % | 44,678 |
| max | not estimated | 67.2 % | 73,400 |
Estimation methodology
The effort setting says how much the model reasons before answering: the higher it is, the more tokens it writes, and the more electricity the task needs. Tokens per task are measured by Epoch AI.
Electricity: Projet Celsius estimate. Tokens of the task × electricity ofwriting 1,000 tokens for the size of the model (AI Impact Database, IA-0011), × the data centre overhead (PUE). The scope covers computing on the servers and cooling; it does not cover chip manufacturing, training, the network or the device. CursorBench counts tokens read and written together: the range runs from "all read" to "all written". DeepSWE counts tokens written: the range starts from writing alone.
Model size unknown: electricity use is not estimated. Benchmark: a quick question to an assistant needs about 0.3 Wh.
GPT-5.6 Luna among OpenAI's models, general intelligence
Epoch AI ECI index and its 95% interval, by release date; 14 OpenAI models released in 2026 and measured by the ECI index
Dot: the index measured, at the release dateLine: the 95% intervalGPT-5.6 Luna5 names in the "Table" tab
Source: Epoch AI, "Capabilities & benchmarking", ECI index. CC BY 4.0 licence.
Continue in the ranking
The full ranking →CompanyOpenAI14models measured, of which 10 with an entryIts assistant, its models, its governance and the electricity of its data centres.The entry →FamilyOpenAIGPT Luna2measured versionsThe versions of the family, their release and their rank in each benchmark.The family →AssistantChatGPT62out of 100, 3rd out of 10The assistant in the ranking that offers GPT-5.6 Luna.The entry →The hub newsletter
This month's ranking, news on the impact of AI and one figure from the AI Impact Database. One newsletter a month at most, free of charge. Past issues
