token.app › Compare › Qwen2.5 72B Instruct vs Qwen3.8 Max

Qwen2.5 72B Instruct vs Qwen3.8 Max

Qwen3.8 Max leads on 2 of 2 shared benchmarks. Qwen2.5 72B Instruct is 8.1× cheaper per token on a blended 3:1 basis. Qwen3.8 Max accepts the larger context window (1M).

Head to head
Blended price uses a 3:1 input:output mix
Qwen2.5 72B InstructQwen3.8 Max
ProviderAlibabaAlibaba
Input $/1M$0.360$2.00
Output $/1M$0.400$6.00
Blended $/1M$0.370$3.00
Context window33K1M
Max output16K131K
ReleasedSep 2024Aug 2026
LicenceOpen weightsProprietary
GPQA Diamond 49.1% 92.7%
OTIS Mock AIME 8.1% 99.4%
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…
  • Costs less per token — $0.370 vs $3.00 blended
  • Open weights — self-hostable
Choose Qwen3.8 Max if…
  • Higher GPQA Diamond (92.7% vs 49.1%)
  • Higher OTIS Mock AIME (99.4% vs 8.1%)
  • Larger context window (1M)
  • Newer model (released Aug 2026)
FAQ
Which is better, Qwen2.5 72B Instruct or Qwen3.8 Max?
Across the 2 benchmarks both models have independently-run scores for, Qwen2.5 72B Instruct leads on 0 and Qwen3.8 Max leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Qwen2.5 72B Instruct cheaper than Qwen3.8 Max?
Qwen2.5 72B Instruct is cheaper: $0.370 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $0.360 vs $2.00. Output alone: $0.400 vs $6.00.
What context windows do Qwen2.5 72B Instruct and Qwen3.8 Max have?
Qwen2.5 72B Instruct: 32,768 tokens. Qwen3.8 Max: 1,000,000 tokens.
Who makes Qwen2.5 72B Instruct and Qwen3.8 Max?
Qwen2.5 72B Instruct is made by Alibaba. Qwen3.8 Max is made by Alibaba.
Related comparisons
Qwen2.5 72B Instruct full details Qwen3.8 Max 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 DeepSeek V4 Flash Latest Qwen2.5 72B Instruct vs DeepSeek V4 Flash 0731 Qwen2.5 72B Instruct vs Inkling Small Qwen2.5 72B Instruct vs Qwen3.7 Flash