Qwen3 235B-A22B vs Qwen2.5 72B
Qwen2.5 72B is cheaper on output tokens. Choose Qwen3 235B-A22B or Qwen2.5 72B based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3 235B-A22B | Qwen2.5 72B |
|---|---|---|
| Provider | Alibaba | NanoGPT |
| Input / 1M tokens | $0.70 | $0.36 |
| Output / 1M tokens | $2.80 | $0.40 |
| Context window | 131K | 131K |
| Parameters | 235B | 73B |
| Open weights | Yes | Yes |
| Released | Apr 2025 | Jul 2025 |
| FrontierMath score | 8.5 | — |
| Epoch Capabilities Index score | 144 | 129 |
| GPQA Diamond score | 80.0 | — |
| LMArena (Chatbot Arena) Elo score | 1415 | — |
FAQ
Is Qwen3 235B-A22B or Qwen2.5 72B cheaper?
Qwen2.5 72B is cheaper on output tokens ($0.40 vs $2.80 per 1M).
Which has the larger context window, Qwen3 235B-A22B or Qwen2.5 72B?
Both models offer a similar context window.
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.