Model Comparison
Qwen3.5 397b vs Qwen3.8 Max 0902
Qwen3.5 397b ranks #87 on the AI IQ leaderboard with an estimated IQ of 109, while Qwen3.8 Max 0902 ranks #29 on the AI IQ leaderboard with an estimated IQ of 125. The table below puts the two models side by side across the seven capability dimensions, emotional reasoning, cost, speed, and context window.
Where They Sit on the IQ Bell Curve
Both models highlighted on the standard normal IQ distribution of every tracked model
| Qwen3.5 397bAlibaba | Qwen3.8 Max 0902Alibaba | |
|---|---|---|
| Rank | #87 | #29 |
| IQ | 109 | 125 |
| Abstract Reasoning | 81 | 107 |
| Mathematical Reasoning | 113 | 131 |
| Academic Reasoning | 121 | 131 |
| Programmatic Reasoning | 110 | 140 |
| Computer Use | 114 | 121 |
| Reliability | 117 | 120 |
| Knowledge Work | 109 | 129 |
| Emotional Reasoning | 108 | — |
| Effective Cost / 1M Tokens | $4.90 | $20.79 |
| Sticker Price / 1M I/O Tokens | $4.20 | $8.00 |
| Speed | 58 tok/s | 40 tok/s |
| Context Window | 262K | 1M |
| Released | 2026-02-16 | 2026-09-02 |
| Open Weights | Yes | No |
More comparisons
- Qwen3.5 397b vs Deepseek V4 Pro
- Qwen3.5 397b vs Fable 5.1
- Qwen3.5 397b vs Gemini 4 Carbon
- Qwen3.5 397b vs Glm 5.3
- Qwen3.5 397b vs GPT 6 Astra
- Qwen3.5 397b vs Grok 4.7
- Qwen3.5 397b vs Kimi K3.1 Pro
- Qwen3.5 397b vs Mimo V2.6 Pro
- Qwen3.5 397b vs Minimax M3
- Qwen3.5 397b vs Muse Wonder Full
- Qwen3.8 Max 0902 vs Deepseek V4 Pro
- Qwen3.8 Max 0902 vs Fable 5.1
- Qwen3.8 Max 0902 vs Gemini 4 Carbon
- Qwen3.8 Max 0902 vs Glm 5.3
- Qwen3.8 Max 0902 vs GPT 6 Astra
- Qwen3.8 Max 0902 vs Grok 4.7
- All comparisons