OpenAI
GPT-5.6 Luna
Closed weights
- Intelligence
- 15.5
- Rank 302 of 744 measured models
- Coding
- 39.3
- Rank 157 of 298 measured models
- Output speed
- 118 t/s
- Rank 136 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
- $0.0101
- Rank 13 of 193 measured models
GPT-5.6 Luna (Non-reasoning) scores 15.5 on the Artificial Analysis Intelligence Index, ranking 302nd of 744 measured models. The closest models on this index are Gemini 3.1 Flash-Lite (15.6), K2 Horizon 3.7B (15.6), and Qwen3 Max (15.6). At $0.45 per million tokens (3:1 input/output blended price), it is cheaper than Gemini 3.1 Flash-Lite ($0.563) and Qwen3 Max ($2.40). With an output speed of 118 t/s, it is faster than Qwen3 Max (61.2 t/s), slower than Gemini 3.1 Flash-Lite (342 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Gemini 3.1 Flash-Lite
Google · $0.563 · 342 t/s
15.6+0.1$0.563342 t/sCompare - K2 Horizon 3.7B
Institute of Foundation Models · — · —
15.6+0.1——Compare - Qwen3 Max
Alibaba · $2.40 · 61.2 t/s
15.6+0.1$2.4061.2 t/sCompare - Claude 4.5 Haiku
Anthropic · $2 · 87.8 t/s
15.4−0.1$287.8 t/sCompare
