token.app › Compare › Claude Sonnet 4.5 vs Qwen3.8 Max
Claude Sonnet 4.5 vs Qwen3.8 Max
Qwen3.8 Max leads on 5 of 5 shared benchmarks. Qwen3.8 Max is 2.0× cheaper per token on a blended 3:1 basis.
Head to head
Blended price uses a 3:1 input:output mix
| Claude Sonnet 4.5 | Qwen3.8 Max | |
|---|---|---|
| Provider | Anthropic | Alibaba |
| Input $/1M | $3.00 | $2.00 |
| Output $/1M | $15.00 | $6.00 |
| Blended $/1M | $6.00 | $3.00 |
| Context window | 1M | 1M |
| Max output | 64K | 131K |
| Released | Sep 2025 | Aug 2026 |
| Licence | Proprietary | Proprietary |
| GPQA Diamond | 82.3% | 92.7% |
| FrontierMath T1–3 | 23.9% | 74.7% |
| FrontierMath T4 | 2.4% | 46.3% |
| SimpleQA Verified | 23.6% | 46.3% |
| OTIS Mock AIME | 77.8% | 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 Claude Sonnet 4.5 if…
- No clear advantage on the data we hold.
Choose Qwen3.8 Max if…
- Costs less per token — $3.00 vs $6.00 blended
- Higher GPQA Diamond (92.7% vs 82.3%)
- Higher FrontierMath T1–3 (74.7% vs 23.9%)
- Higher FrontierMath T4 (46.3% vs 2.4%)
- Higher SimpleQA Verified (46.3% vs 23.6%)
- Newer model (released Aug 2026)
FAQ
Which is better, Claude Sonnet 4.5 or Qwen3.8 Max?
Across the 5 benchmarks both models have independently-run scores for, Claude Sonnet 4.5 leads on 0 and Qwen3.8 Max leads on 5. Benchmarks are one input — price and context window are on this page too.
Is Claude Sonnet 4.5 cheaper than Qwen3.8 Max?
Qwen3.8 Max is cheaper: $3.00 versus $6.00 per million tokens blended at 3:1 input:output. Input alone: $3.00 vs $2.00. Output alone: $15.00 vs $6.00.
What context windows do Claude Sonnet 4.5 and Qwen3.8 Max have?
Claude Sonnet 4.5: 1,000,000 tokens. Qwen3.8 Max: 1,000,000 tokens.
Who makes Claude Sonnet 4.5 and Qwen3.8 Max?
Claude Sonnet 4.5 is made by Anthropic. Qwen3.8 Max is made by Alibaba.
Related comparisons