Model Comparison
Qwen3.8 2.4t A95b vs Qwen4 Max
Qwen3.8 2.4t A95b ranks #46 on the AI IQ leaderboard with an estimated IQ of 122, while Qwen4 Max ranks #24 on the AI IQ leaderboard with an estimated IQ of 128. 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
| Qwen3.8 2.4t A95bAlibaba | Qwen4 MaxAlibaba | |
|---|---|---|
| Rank | #46 | #24 |
| IQ | 122 | 128 |
| Abstract Reasoning | 100 | 106 |
| Mathematical Reasoning | 126 | 131 |
| Academic Reasoning | 131 | 130 |
| Programmatic Reasoning | 131 | 140 |
| Computer Use | 126 | 119 |
| Reliability | 118 | 140 |
| Knowledge Work | 126 | 128 |
| Emotional Reasoning | — | — |
| Effective Cost / 1M Tokens | $13.22 | $15.59 |
| Sticker Price / 1M I/O Tokens | $8.00 | $6.00 |
| Speed | 41 tok/s | — |
| Context Window | 1.0M | 1M |
| Released | 2026-08-08 | 2026-11-16 |
| Open Weights | Yes | No |
More comparisons
- Qwen3.8 2.4t A95b vs Deepseek V4 Pro
- Qwen3.8 2.4t A95b vs Fable 5.2
- Qwen3.8 2.4t A95b vs Gemini 4 Carbon
- Qwen3.8 2.4t A95b vs Glm 5.3
- Qwen3.8 2.4t A95b vs GPT 6.2 Astra
- Qwen3.8 2.4t A95b vs Grok 4.7
- Qwen3.8 2.4t A95b vs Kimi K3.1 Pro
- Qwen3.8 2.4t A95b vs Mimo V2.6 Pro
- Qwen3.8 2.4t A95b vs Minimax M3
- Qwen3.8 2.4t A95b vs Muse Wonder Full
- Qwen4 Max vs Deepseek V4 Pro
- Qwen4 Max vs Fable 5.2
- Qwen4 Max vs Gemini 4 Carbon
- Qwen4 Max vs Glm 5.3
- Qwen4 Max vs GPT 6.2 Astra
- Qwen4 Max vs Grok 4.7
- All comparisons