Qwen3 235B-A22B vs Kimi K2 Instruct
Kimi K2 Instruct is cheaper on output tokens, while Qwen3 235B-A22B offers a larger context window. Choose Qwen3 235B-A22B or Kimi K2 Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3 235B-A22B | Kimi K2 Instruct |
|---|---|---|
| Provider | Alibaba | Cortecs |
| Input / 1M tokens | $0.70 | $0.55 |
| Output / 1M tokens | $2.80 | $2.65 |
| Context window | 131K | 131K |
| Parameters | 235B | — |
| Open weights | Yes | Yes |
| Released | Apr 2025 | Jul 2025 |
| LMArena (Chatbot Arena) Elo score | 1415 | — |
| GPQA Diamond score | 80.0 | — |
| FrontierMath score | 8.5 | — |
| Epoch Capabilities Index score | 144 | — |
| SWE-bench Verified score | — | 53.4 |
FAQ
Is Qwen3 235B-A22B or Kimi K2 Instruct cheaper?
Kimi K2 Instruct is cheaper on output tokens ($2.65 vs $2.80 per 1M).
Which has the larger context window, Qwen3 235B-A22B or Kimi K2 Instruct?
Qwen3 235B-A22B has the larger context window (131K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.