token.app › Compare › Qwen2.5 72B Instruct vs GPT-5.6 Luna

Qwen2.5 72B Instruct vs GPT-5.6 Luna

GPT-5.6 Luna leads on 2 of 2 shared benchmarks. GPT-5.6 Luna is 1.6× 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
Qwen2.5 72B InstructGPT-5.6 Luna
ProviderAlibabaOpenAI
Input $/1M$0.360$0.100
Output $/1M$0.400$0.600
Blended $/1M$0.370$0.225
Context window33K1.1M
Max output16K128K
ReleasedSep 2024Jul 2026
LicenceOpen weightsProprietary
GPQA Diamond 49.1% 91.6%
OTIS Mock AIME 8.1% 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 Qwen2.5 72B Instruct if…
  • Open weights — self-hostable
Choose GPT-5.6 Luna if…
  • Costs less per token — $0.225 vs $0.370 blended
  • Higher GPQA Diamond (91.6% vs 49.1%)
  • Higher OTIS Mock AIME (98.3% vs 8.1%)
  • Larger context window (1.1M)
  • Newer model (released Jul 2026)
FAQ
Which is better, Qwen2.5 72B Instruct or GPT-5.6 Luna?
Across the 2 benchmarks both models have independently-run scores for, Qwen2.5 72B Instruct 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 Qwen2.5 72B Instruct cheaper than GPT-5.6 Luna?
GPT-5.6 Luna is cheaper: $0.225 versus $0.370 per million tokens blended at 3:1 input:output. Input alone: $0.360 vs $0.100. Output alone: $0.400 vs $0.600.
What context windows do Qwen2.5 72B Instruct and GPT-5.6 Luna have?
Qwen2.5 72B Instruct: 32,768 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes Qwen2.5 72B Instruct and GPT-5.6 Luna?
Qwen2.5 72B Instruct is made by Alibaba. GPT-5.6 Luna is made by OpenAI.
Related comparisons
Qwen2.5 72B Instruct full details GPT-5.6 Luna full details Qwen2.5 72B Instruct vs Ling 3.0 Tiny (free) Qwen2.5 72B Instruct vs Muse Spark 1.2 Qwen2.5 72B Instruct vs Qwen3.8 Max Qwen2.5 72B Instruct vs DeepSeek V4 Flash Latest Qwen2.5 72B Instruct vs DeepSeek V4 Flash 0731 Qwen2.5 72B Instruct vs Inkling Small