token.app › Compare › Qwen2.5 72B Instruct vs Llama 4 Scout

Qwen2.5 72B Instruct vs Llama 4 Scout

Qwen2.5 72B Instruct and Llama 4 Scout split the 2 shared benchmarks evenly. Llama 4 Scout is 2.5× 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
Qwen2.5 72B InstructLlama 4 Scout
ProviderAlibabaMeta
Input $/1M$0.360$0.100
Output $/1M$0.400$0.300
Blended $/1M$0.370$0.150
Context window33K1.3M
Max output16K16K
ReleasedSep 2024Apr 2025
LicenceOpen weightsOpen weights
GPQA Diamond 49.1% 51.8%
OTIS Mock AIME 8.1% 7.8%
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…
  • Higher OTIS Mock AIME (8.1% vs 7.8%)
Choose Llama 4 Scout if…
  • Costs less per token — $0.150 vs $0.370 blended
  • Higher GPQA Diamond (51.8% vs 49.1%)
  • Larger context window (1.3M)
  • Newer model (released Apr 2025)
FAQ
Which is better, Qwen2.5 72B Instruct or Llama 4 Scout?
Across the 2 benchmarks both models have independently-run scores for, Qwen2.5 72B Instruct leads on 1 and Llama 4 Scout leads on 1. Benchmarks are one input — price and context window are on this page too.
Is Qwen2.5 72B Instruct cheaper than Llama 4 Scout?
Llama 4 Scout is cheaper: $0.150 versus $0.370 per million tokens blended at 3:1 input:output. Input alone: $0.360 vs $0.100. Output alone: $0.400 vs $0.300.
What context windows do Qwen2.5 72B Instruct and Llama 4 Scout have?
Qwen2.5 72B Instruct: 32,768 tokens. Llama 4 Scout: 1,310,720 tokens.
Who makes Qwen2.5 72B Instruct and Llama 4 Scout?
Qwen2.5 72B Instruct is made by Alibaba. Llama 4 Scout is made by Meta.
Related comparisons
Qwen2.5 72B Instruct full details Llama 4 Scout 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