Model Comparison
Deepseek V3.2 vs Gemini 4 Carbon
Deepseek V3.2 ranks #118 on the AI IQ leaderboard with an estimated IQ of 101, while Gemini 4 Carbon ranks #5 on the AI IQ leaderboard with an estimated IQ of 139. 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
| Deepseek V3.2DeepSeek | Gemini 4 CarbonGoogle | |
|---|---|---|
| Rank | #118 | #5 |
| IQ | 101 | 139 |
| Abstract Reasoning | 79 | 120 |
| Mathematical Reasoning | 103 | 145 |
| Academic Reasoning | 118 | 136 |
| Programmatic Reasoning | 111 | 153 |
| Computer Use | 101 | 155 |
| Reliability | 101 | 135 |
| Knowledge Work | 96 | 130 |
| Emotional Reasoning | — | — |
| Effective Cost / 1M Tokens | $1.84 | — |
| Sticker Price / 1M I/O Tokens | $0.70 | — |
| Speed | 33 tok/s | — |
| Context Window | — | — |
| Released | 2025-12-01 | 2026-10-28 |
| Open Weights | Yes | No |
More comparisons
- Deepseek V3.2 vs Deepseek V4 Pro
- Deepseek V3.2 vs Fable 5.1
- Deepseek V3.2 vs Glm 5.3
- Deepseek V3.2 vs GPT 6 Astra
- Deepseek V3.2 vs Grok 4.7
- Deepseek V3.2 vs Kimi K3.1 Pro
- Deepseek V3.2 vs Mimo V2.6 Pro
- Deepseek V3.2 vs Minimax M3
- Deepseek V3.2 vs Muse Wonder Full
- Deepseek V3.2 vs Qwen3.8 Max 0902
- Gemini 4 Carbon vs Deepseek V4 Pro
- Gemini 4 Carbon vs Fable 5.1
- Gemini 4 Carbon vs Glm 5.3
- Gemini 4 Carbon vs GPT 6 Astra
- Gemini 4 Carbon vs Grok 4.7
- Gemini 4 Carbon vs Kimi K3.1 Pro
- All comparisons