Which models should I use?
In practice, there is no single correct answer! Below is a curated list based on JieKou AI internal testing, community feedback, and external benchmarks. We recommend using it as a starting point, and we will update it regularly as new models become available.- Model sizes are labeled as small, medium, or large
- For the best latency, use small or medium models. For the best quality, use large models or fine-tune medium or small models.
- You can explore all models in the JieKou AI model library
| Use Case | Recommended Models |
|---|---|
| Code Generation and Reasoning | claude series (large/medium/small) |
| Deepseek-r1-0528 (large) | |
| Deepseek-v3-0324 (large) | |
| Qwen3-Coder-480B-A35B-Instruct (large) | |
| Qwen3-235B-A22B-Instruct-2507 (large) | |
| Kimi-K2-Instruct (medium) | |
| GLM-4.5 (medium) | |
| General Reasoning and Planning | Deepseek-r1-0528 (large) |
| Deepseek-v3-0324 (large) | |
| Qwen-2.5-72b-instruct (medium) | |
| Llama-3.3-70b-instruct (medium) | |
| Function Calling and Tool Use | Qwen3-235b-a22b-fp8 (large) |
| Qwen 3 series (large/medium/small) | |
| Long Context and Summarization | Llama-4-maverick-17b-128e-instruct-fp8 (large) |
| Llama-4-scout-17b-16e-instruct (medium) | |
| Vision and Document Understanding | Llama-4-maverick-17b-128e-instruct-fp8 (large) |
| Qwen2.5-vl-72b-instruct (medium) | |
| Llama-4-scout-17b-16e-instruct (medium) | |
| Low-Latency Natural Language Understanding and Extraction | Llama-3.1-8b-instruct (small) |