Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works
Alibaba models by SI-IQ
Alibaba has 43 models with independent benchmark results in our data. The best ranked is Qwen3.7-Max with an SI-IQ of 125.
Models
| 1 | Qwen3.7-Max Alibaba | 125122–128 | 10 |
| 2 | Qwen3.6 27Bopen Alibaba | 115110–119 | 6 |
| 3 | Qwen3.7-Plus Alibaba | 115110–119 | 6 |
| 4 | Qwen3.5 397B-A17Bopen Alibaba | 114109–118 | 6 |
| 5 | Qwen3-235B-A22B-Thinking (Jul 2025)open Alibaba | 111105–118 | 6 |
| 6 | Qwen 3.6 35B-A3Bopen Alibaba | 111107–115 | 6 |
| 7 | Qwen3-32Bopen Alibaba | 9589–100 | 6 |
| 8 | Qwen 3.8 Max Alibaba | 130127–133 | 7 results from fewer than 2 evaluators |
| 9 | Qwen3.8 Max (0902) Alibaba | 127123–130 | 6 results from fewer than 2 evaluators |
| 10 | Qwen3.8 Flash Alibaba | 125111–138 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 11 | Qwen 3.8 27Bopen Alibaba | 120106–133 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 12 | Qwen 3.6 Max (Preview) Alibaba | 118112–124 | 5 results from fewer than 2 evaluators |
| 13 | Qwen 3.6 Plus Alibaba | 113109–117 | 7 results from fewer than 2 evaluators |
| 14 | Qwen3.5-122B-A10Bopen Alibaba | 112103–121 | 3 results from fewer than 5 benchmarks |
| 15 | Qwen 3.5 Plus (hosted 397B-A17B) Alibaba | 109103–115 | 5 results from fewer than 2 evaluators |
| 16 | Qwen 3.6 Flash Alibaba | 107103–111 | 6 results from fewer than 2 evaluators |
| 17 | Qwen3.7 Flash Alibaba | 107103–112 | 4 results from fewer than 5 benchmarks; results from fewer than 2 evaluators |
| 18 | Qwen 3.5 Flash (hosted 35B-A3B) Alibaba | 107103–111 | 6 results from fewer than 2 evaluators |
| 19 | Qwen3-Max Alibaba | 106103–110 | 6 results from fewer than 2 evaluators |
| 20 | Qwen3.5-35B-A3Bopen Alibaba | 106100–112 | 4 results from fewer than 5 benchmarks |
| 21 | Qwen3.5-9Bopen Alibaba | 10195–107 | 4 results from fewer than 5 benchmarks |
| 22 | Qwen3-30B-A3B-Thinking (Jul 2025)open Alibaba | 10093–106 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 23 | Qwen3-235B-A22B-Instruct (Jul 2025)open Alibaba | 9685–107 | 3 results from fewer than 5 benchmarks; results in fewer than 3 areas |
| 24 | Qwen3.5-4Bopen Alibaba | 9688–103 | 1 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 25 | Qwen3-30B-A3Bopen Alibaba | 9488–100 | 4 results from fewer than 5 benchmarks |
| 26 | Qwen3-14Bopen Alibaba | 9387–99 | 5 results from fewer than 5 benchmarks |
| 27 | QwQ-32Bopen Alibaba | 9286–98 | 3 results from fewer than 5 benchmarks |
| 28 | Qwen3-30B-A3B-Instruct (Jul 2025)open Alibaba | 9186–97 | 5 results from fewer than 5 benchmarks |
| 29 | Qwen3-8Bopen Alibaba | 9184–97 | 3 results from fewer than 5 benchmarks |
| 30 | QWQ-Plus Alibaba | 9079–102 | 1 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 31 | Qwen3-235B-A22Bopen Alibaba | 8580–91 | 3 results from fewer than 5 benchmarks |
| 32 | Qwen3-Coder-480B-A35Bopen Alibaba | 8572–98 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 33 | Qwen2.5-Max Alibaba | 7873–82 | 4 results from fewer than 5 benchmarks |
| 34 | Qwen3-4Bopen Alibaba | 7765–89 | 1 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 35 | Qwen Plus (Jan 2025) Alibaba | 7671–81 | 3 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 36 | Qwen2.5-Coder-32B-Instructopen Alibaba | 7559–90 | 1 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 37 | Qwen2.5-72Bopen Alibaba | 7268–77 | 5 results from fewer than 5 benchmarks |
| 38 | Qwen2.5-32Bopen Alibaba | 7166–76 | 3 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 39 | Qwen-Turbo Alibaba | 6964–75 | 3 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 40 | Qwen3-1.7Bopen Alibaba | 6557–73 | 3 results from fewer than 5 benchmarks |
| 41 | Qwen3-0.6Bopen Alibaba | 6445–83 | 1 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 42 | Qwen2-72Bopen Alibaba | 6458–69 | 2 results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators |
| 43 | Qwen2.5-7Bopen Alibaba | 5141–60 | 4 results from fewer than 5 benchmarks |
Data sources: Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); LiteLLM, model_prices_and_context_window.json (MIT); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter (licences and changes).