Model Comparison
Gemma 4 26b A4b vs Gemma 4 31b
Gemma 4 26b A4b ranks #131 on the AI IQ leaderboard with an estimated IQ of 99, while Gemma 4 31b ranks #120 on the AI IQ leaderboard with an estimated IQ of 101. 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
| Gemma 4 26b A4bGoogle | Gemma 4 31bGoogle | |
|---|---|---|
| Rank | #131 | #120 |
| IQ | 99 | 101 |
| Abstract Reasoning | 86 | 86 |
| Mathematical Reasoning | 92 | 94 |
| Academic Reasoning | 112 | 117 |
| Programmatic Reasoning | 97 | 97 |
| Computer Use | 98 | 101 |
| Reliability | 110 | 108 |
| Knowledge Work | 100 | 103 |
| Emotional Reasoning | 108 | 105 |
| Effective Cost / 1M Tokens | $0.14 | $0.14 |
| Sticker Price / 1M I/O Tokens | $0.47 | $0.47 |
| Speed | 94 tok/s | 35 tok/s |
| Context Window | 256K | 256K |
| Released | 2026-04-02 | 2026-04-02 |
| Open Weights | Yes | Yes |
More comparisons
- Gemma 4 26b A4b vs Deepseek V4 Pro
- Gemma 4 26b A4b vs Fable 5.1
- Gemma 4 26b A4b vs Gemini 4 Carbon
- Gemma 4 26b A4b vs Glm 5.3
- Gemma 4 26b A4b vs GPT 6 Astra
- Gemma 4 26b A4b vs Grok 4.7
- Gemma 4 26b A4b vs Kimi K3.1 Pro
- Gemma 4 26b A4b vs Mimo V2.6 Pro
- Gemma 4 26b A4b vs Minimax M3
- Gemma 4 26b A4b vs Muse Wonder Full
- Gemma 4 26b A4b vs Qwen3.8 Max 0902
- Gemma 4 31b vs Deepseek V4 Pro
- Gemma 4 31b vs Fable 5.1
- Gemma 4 31b vs Gemini 4 Carbon
- Gemma 4 31b vs Glm 5.3
- Gemma 4 31b vs GPT 6 Astra
- All comparisons