token.app › Compare › Qwen3.7 Max vs Qwen3.8 Max
Qwen3.7 Max vs Qwen3.8 Max
Qwen3.8 Max leads on 4 of 5 shared benchmarks. Qwen3.7 Max is 1.4× cheaper per token on a blended 3:1 basis.
Head to head
Blended price uses a 3:1 input:output mix
| Qwen3.7 Max | Qwen3.8 Max | |
|---|---|---|
| Provider | Alibaba | Alibaba |
| Input $/1M | $1.48 | $2.00 |
| Output $/1M | $4.42 | $6.00 |
| Blended $/1M | $2.21 | $3.00 |
| Context window | 1M | 1M |
| Max output | 131K | 131K |
| Released | May 2026 | Aug 2026 |
| Licence | Proprietary | Proprietary |
| GPQA Diamond | 90.9% | 92.7% |
| FrontierMath T1–3 | 64.6% | 74.7% |
| FrontierMath T4 | 34.1% | 46.3% |
| SimpleQA Verified | 58.5% | 46.3% |
| OTIS Mock AIME | 95.6% | 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 Qwen3.7 Max if…
- Costs less per token — $2.21 vs $3.00 blended
- Higher SimpleQA Verified (58.5% vs 46.3%)
Choose Qwen3.8 Max if…
- Higher GPQA Diamond (92.7% vs 90.9%)
- Higher FrontierMath T1–3 (74.7% vs 64.6%)
- Higher FrontierMath T4 (46.3% vs 34.1%)
- Higher OTIS Mock AIME (99.4% vs 95.6%)
- Newer model (released Aug 2026)
FAQ
Which is better, Qwen3.7 Max or Qwen3.8 Max?
Across the 5 benchmarks both models have independently-run scores for, Qwen3.7 Max leads on 1 and Qwen3.8 Max leads on 4. Benchmarks are one input — price and context window are on this page too.
Is Qwen3.7 Max cheaper than Qwen3.8 Max?
Qwen3.7 Max is cheaper: $2.21 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $1.48 vs $2.00. Output alone: $4.42 vs $6.00.
What context windows do Qwen3.7 Max and Qwen3.8 Max have?
Qwen3.7 Max: 1,000,000 tokens. Qwen3.8 Max: 1,000,000 tokens.
Who makes Qwen3.7 Max and Qwen3.8 Max?
Qwen3.7 Max is made by Alibaba. Qwen3.8 Max is made by Alibaba.