token.app › Compare › Qwen3.5 397B A17B vs Claude Opus 5
Qwen3.5 397B A17B vs Claude Opus 5
Claude Opus 5 leads on 3 of 3 shared benchmarks. Qwen3.5 397B A17B is 7.8× cheaper per token on a blended 3:1 basis. Claude Opus 5 accepts the larger context window (1M).
Head to head
Blended price uses a 3:1 input:output mix
| Qwen3.5 397B A17B | Claude Opus 5 | |
|---|---|---|
| Provider | Alibaba | Anthropic |
| Input $/1M | $0.500 | $5.00 |
| Output $/1M | $3.60 | $25.00 |
| Blended $/1M | $1.27 | $10.00 |
| Context window | 262K | 1M |
| Max output | 236K | 128K |
| Released | Feb 2026 | Jul 2026 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 86.4% | 93.9% |
| FrontierMath T1–3 | 31.2% | 85.6% |
| OTIS Mock AIME | 88.9% | 98.9% |
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 Qwen3.5 397B A17B if…
- Costs less per token — $1.27 vs $10.00 blended
- Open weights — self-hostable
Choose Claude Opus 5 if…
- Higher GPQA Diamond (93.9% vs 86.4%)
- Higher FrontierMath T1–3 (85.6% vs 31.2%)
- Higher OTIS Mock AIME (98.9% vs 88.9%)
- Larger context window (1M)
- Newer model (released Jul 2026)
FAQ
Which is better, Qwen3.5 397B A17B or Claude Opus 5?
Across the 3 benchmarks both models have independently-run scores for, Qwen3.5 397B A17B leads on 0 and Claude Opus 5 leads on 3. Benchmarks are one input — price and context window are on this page too.
Is Qwen3.5 397B A17B cheaper than Claude Opus 5?
Qwen3.5 397B A17B is cheaper: $1.27 versus $10.00 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $5.00. Output alone: $3.60 vs $25.00.
What context windows do Qwen3.5 397B A17B and Claude Opus 5 have?
Qwen3.5 397B A17B: 262,144 tokens. Claude Opus 5: 1,000,000 tokens.
Who makes Qwen3.5 397B A17B and Claude Opus 5?
Qwen3.5 397B A17B is made by Alibaba. Claude Opus 5 is made by Anthropic.
Related comparisons