OpenAI
GPT-5.6 Luna
ReasoningClosed weights
- Intelligence
- 21.0
- Rank 230 of 744 measured models
- Coding
- 44.2
- Rank 141 of 298 measured models
- Output speed
- 120 t/s
- Rank 129 of 403 measured models
- Price/1M
- $0.45
- Rank 256 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.0098
- Rank 12 of 193 measured models
GPT-5.6 Luna (Low) scores 21.0 on the Artificial Analysis Intelligence Index, ranking 230th of 744 measured models. The closest models on this index are Qwen3.6 27B (21.4), MiniMax-M2.1 (20.9), and GPT-5.4 nano (20.7). At $0.45 per million tokens (3:1 input/output blended price), it is cheaper than Qwen3.6 27B ($1.35) and MiniMax-M2.1 ($0.525), priced close to GPT-5.4 nano ($0.463). With an output speed of 120 t/s, it is faster than Qwen3.6 27B (55.6 t/s) and MiniMax-M2.1 (62.2 t/s), slower than GPT-5.4 nano (166 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Qwen3.6 27B
Alibaba · $1.35 · 55.6 t/s
21.4+0.4$1.3555.6 t/sCompare - MiniMax-M2.1
MiniMax · $0.525 · 62.2 t/s
20.9−0.1$0.52562.2 t/sCompare - GPT-5.4 nano
OpenAI · $0.463 · 166 t/s
20.7−0.3$0.463166 t/sCompare - GPT-5 Mini (batch)
OpenAI · — · —
20.6−0.4——Compare
