OpenAIProvisional

GPT-5.6 Luna

GPT-5.6 / Luna · gpt-5.6-luna

Automatically tracked from OpenAI's official model catalog.

Objective score

37.1

Confidence

79%

Price evidence

$0.2 input / $1.2 output per 1M tokens

Support this model Compare trend Official source

Other primary tiers in this family

Scenario evidence

Six task-specific rankings

Feature development#22Obj. 37.10 · 0%Debug and repair#8Obj. 53.40 · 0%Refactoring#8Obj. 53.40 · 0%Code review#8Obj. 55.40 · 0%Large-repo agent work#22Obj. 32.80 · 0%Frontend / UI#9Obj. 53.40 · 0%

Evidence state

Signal coverage

Benchmarks: 2
Rank points: 7
Usage: 3
Agent: 0
Sources: 3

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 71.4
Openrouter Usage: 3.1
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#34 · 37

Aug 1#34 · 37

Jul 31#38 · 36

Jul 31#38 · 36

Jul 31#38 · 36

Jul 31#38 · 36

Usage signals

OpenRouter coding12.5%

Overall10.3%

OpenRouter3.1%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official OpenAI model catalog Artificial Analysis Coding Agents · ok WebDev Arena · ok OpenAI API models · ok