token.app › Compare › Qwen3 235B A22B vs GPT-5.6 Luna
Qwen3 235B A22B vs GPT-5.6 Luna
GPT-5.6 Luna leads on 1 of 1 shared benchmarks. GPT-5.6 Luna is 3.5× cheaper per token on a blended 3:1 basis. GPT-5.6 Luna accepts the larger context window (1.1M).
Head to head
Blended price uses a 3:1 input:output mix
| Qwen3 235B A22B | GPT-5.6 Luna | |
|---|---|---|
| Provider | Alibaba | OpenAI |
| Input $/1M | $0.455 | $0.100 |
| Output $/1M | $1.82 | $0.600 |
| Blended $/1M | $0.796 | $0.225 |
| Context window | 131K | 1.1M |
| Max output | 8K | 128K |
| Released | Apr 2025 | Jul 2026 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 70.7% | 91.6% |
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 Qwen3 235B A22B if…
- Open weights — self-hostable
Choose GPT-5.6 Luna if…
- Costs less per token — $0.225 vs $0.796 blended
- Higher GPQA Diamond (91.6% vs 70.7%)
- Larger context window (1.1M)
- Newer model (released Jul 2026)
FAQ
Which is better, Qwen3 235B A22B or GPT-5.6 Luna?
Across the 1 benchmark both models have independently-run scores for, Qwen3 235B A22B leads on 0 and GPT-5.6 Luna leads on 1. Benchmarks are one input — price and context window are on this page too.
Is Qwen3 235B A22B cheaper than GPT-5.6 Luna?
GPT-5.6 Luna is cheaper: $0.225 versus $0.796 per million tokens blended at 3:1 input:output. Input alone: $0.455 vs $0.100. Output alone: $1.82 vs $0.600.
What context windows do Qwen3 235B A22B and GPT-5.6 Luna have?
Qwen3 235B A22B: 131,072 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes Qwen3 235B A22B and GPT-5.6 Luna?
Qwen3 235B A22B is made by Alibaba. GPT-5.6 Luna is made by OpenAI.