Best Qwen model overall
- models ranked
- 30
- lead over #2
- +5.5
Overall index · read October 21
As of October 21, 2026, Qwen3.8 Max (0902) leads 30 models that qualify, with 45.4 on the overall index, ahead of Qwen3.8 2.4T A95B (39.9) and Qwen3.8 27B (33.7).
| Rank | Model | Overall index | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Qwen3.8 Max (0902) Qwen | 45.4 | 63.5 | $6.00 | |
| 2 | Qwen3.8 2.4T A95B Qwen | 39.9 | Not benchmarked | $6.00 | |
| 3 | Qwen3.8 27B Qwen | 33.7 | 73.6 | $1.35 | |
| 4 | Qwen3.7 Max Qwen | 29.5 | 45.1 | $4.425 | |
| 5 | Qwen3.6 Plus Qwen | 27.0 | 37.4 | $1.95 | |
| 6 | Qwen3.7 Plus Qwen | 25.2 | Not benchmarked | $1.28 | |
| 7 | Qwen3.5-27B Qwen | 22.9 | 22.6 | $2.16 | |
| 8 | Qwen3.5 397B A17B Qwen | 21.4 | 28.6 | $2.34 | |
| 9 | Qwen3.6 27B Qwen | 21.4 | Not benchmarked | $2.00 | |
| 10 | Qwen3.5-35B-A3B Qwen | 19.3 | 7.7 | $1.00 | |
| 11 | Qwen3.6 35B A3B Qwen | 18.2 | Not benchmarked | $0.95 | |
| 12 | Qwen3.5-122B-A10B Qwen | 17.7 | 22.9 | $2.08 | |
| 13 | Qwen3.5-9B Qwen | 13.3 | Not benchmarked | $0.13 | |
| 14 | 12.7 | Not benchmarked | $3.50 | ||
| 15 | 12.0 | Not benchmarked | $0.55 | ||
| 16 | 11.9 | 50.0 | $1.00 | ||
| 17 | 11.2 | Not benchmarked | $1.20 | ||
| 18 | 9.9 | Not benchmarked | $1.90 | ||
| 19 | 9.6 | 60.4 | $0.28 | ||
| 20 | 9.6 | Not benchmarked | $1.10 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Every Qwen model on the overall index, ordered by the Artificial Analysis Intelligence Index, highest first. The index is a composite of evaluations Artificial Analysis runs itself, published on a 0 to 100 scale.
- OpenRouter, fetched
- Artificial Analysis (via OpenRouter), fetched