Qwen3.5 397B-A17B vs Claude 3.5 Haiku
Qwen3.5 397B-A17B is cheaper on output tokens, while Qwen3.5 397B-A17B offers a larger context window. Choose Qwen3.5 397B-A17B or Claude 3.5 Haiku based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3.5 397B-A17B | Claude 3.5 Haiku |
|---|---|---|
| Provider | Alibaba | Helicone |
| Input / 1M tokens | $0.60 | $0.80 |
| Output / 1M tokens | $3.60 | $4.00 |
| Context window | 262K | 200K |
| Parameters | 397B | — |
| Open weights | Yes | No |
| Released | Feb 2026 | Oct 2024 |
| GPQA Diamond score | 86.4 | 38.1 |
| LMArena (Chatbot Arena) Elo score | 1437 | 1255 |
| LMArena WebDev Elo score | 1400 | — |
| LMArena Vision Elo score | 1262 | 1093 |
| Epoch Capabilities Index score | 147 | 127 |
| Aider Polyglot score | — | 28.0 |
| FrontierMath score | — | 0.3 |
FAQ
Is Qwen3.5 397B-A17B or Claude 3.5 Haiku cheaper?
Qwen3.5 397B-A17B is cheaper on output tokens ($3.60 vs $4.00 per 1M).
Which has the larger context window, Qwen3.5 397B-A17B or Claude 3.5 Haiku?
Qwen3.5 397B-A17B has the larger context window (262K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.