Best Qwen model for coding
- Qwen3.8 27B leads
- 74.2
- models ranked
- 8
- lead over #2
- +11.8
Coding index · read October 22
As of October 22, 2026, Qwen3.8 27B leads 8 scored Qwen models with a coding index of 74.2, ahead of Qwen3.8 Max (0902) (62.4) and Qwen3.7 Max (54.1).
The full best LLM for coding ranking combines this benchmark with others.
Ordered by index, highest first. The dots show how many benchmarks stand behind each score.
| Rank | Model | Coding index | Evidence | Output $/Mtok |
|---|---|---|---|---|
| 1 | Qwen3.8 27B Qwen | 74.2 | $2.55 | |
| 2 | Qwen3.8 Max (0902) Qwen | 62.4 | $6.00 | |
| 3 | Qwen3.7 Max Qwen | 54.1 | $4.425 | |
| 4 | Qwen3.6 Plus Qwen | 44.1 | $1.95 | |
| 5 | Qwen3.5-Flash Qwen | 41.1 | $0.26 | |
| 6 | 39.5 | $1.80 | ||
| 7 | Qwen3.6 27B Qwen | 36.8 | $2.70 | |
| 8 | Qwen3.7 Plus Qwen | 33.2 | $1.28 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Every Qwen model with a Vibe Coding Index score, ordered as the ranking orders them: by how many benchmarks stand behind the score, then by the score.
- Aider polyglot leaderboard, fetched
- LiveBench, fetched , board updated October 14, 2026
- SWE-bench (swebench.com), fetched
- LMArena WebDev, fetched