token.app › Compare › Llama 4 Scout vs GPT-5.6 Luna
Llama 4 Scout vs GPT-5.6 Luna
GPT-5.6 Luna leads on 2 of 2 shared benchmarks. Llama 4 Scout is 1.5× cheaper per token on a blended 3:1 basis. Llama 4 Scout accepts the larger context window (1.3M).
Head to head
Blended price uses a 3:1 input:output mix
| Llama 4 Scout | GPT-5.6 Luna | |
|---|---|---|
| Provider | Meta | OpenAI |
| Input $/1M | $0.100 | $0.100 |
| Output $/1M | $0.300 | $0.600 |
| Blended $/1M | $0.150 | $0.225 |
| Context window | 1.3M | 1.1M |
| Max output | 16K | 128K |
| Released | Apr 2025 | Jul 2026 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 51.8% | 91.6% |
| OTIS Mock AIME | 7.8% | 98.3% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Llama 4 Scout if…
- Costs less per token — $0.150 vs $0.225 blended
- Larger context window (1.3M)
- Open weights — self-hostable
Choose GPT-5.6 Luna if…
- Higher GPQA Diamond (91.6% vs 51.8%)
- Higher OTIS Mock AIME (98.3% vs 7.8%)
- Newer model (released Jul 2026)
FAQ
Which is better, Llama 4 Scout or GPT-5.6 Luna?
Across the 2 benchmarks both models have independently-run scores for, Llama 4 Scout leads on 0 and GPT-5.6 Luna leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Llama 4 Scout cheaper than GPT-5.6 Luna?
Llama 4 Scout is cheaper: $0.150 versus $0.225 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.100. Output alone: $0.300 vs $0.600.
What context windows do Llama 4 Scout and GPT-5.6 Luna have?
Llama 4 Scout: 1,310,720 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes Llama 4 Scout and GPT-5.6 Luna?
Llama 4 Scout is made by Meta. GPT-5.6 Luna is made by OpenAI.