OpenAI
GPT-5.6 Luna
ReasoningClosed weights
- Intelligence
- 32.1
- Rank 114 of 744 measured models
- Coding
- 63.3
- Rank 73 of 298 measured models
- Output speed
- 115 t/s
- Rank 143 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
- $0.044
- Rank 33 of 193 measured models
GPT-5.6 Luna (High) scores 32.1 on the Artificial Analysis Intelligence Index, ranking 114th of 744 measured models. The closest models on this index are GPT-5.3 Codex (Xhigh) (32.5), Motif 3 (Beta) (32.3), and Claude Opus 4.6 (batch) (31.9). At $0.45 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.3 Codex (Xhigh) ($4.81). With an output speed of 115 t/s, it is faster than GPT-5.3 Codex (Xhigh) (98.5 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Gemini 3.5 Flash
Google · $3.38 · 177 t/s
32.6+0.5$3.38177 t/sCompare - GPT-5.3 Codex (Xhigh)
OpenAI · $4.81 · 98.5 t/s
32.5+0.4$4.8198.5 t/sCompare - Motif 3 (Beta)
Motif Technologies · — · —
32.3+0.2——Compare - Claude Opus 4.6 (batch)
Anthropic · — · —
31.9−0.2——Compare
