Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Phi-3 Mini Instruct 3.8B
Microsoft
- Gemini 1.0 Ultra
Google
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Phi-3 Mini Instruct 3.8B Microsoft | Gemini 1.0 Ultra | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 5.8 | 5.8 | |
| Coding | — | 17.6 | |
| Math | 0.3 | — | |
| Context window | 4K | Best: 33K | |
| Reasoning | No | No | |
| Open weights | Yes | No |
Intelligence
- Phi-3 Mini Instruct 3.8B
- 5.8
- Gemini 1.0 Ultra
- 5.8
Coding
- Phi-3 Mini Instruct 3.8B
- —
- Gemini 1.0 Ultra
- 17.6
Math
- Phi-3 Mini Instruct 3.8B
- 0.3
- Gemini 1.0 Ultra
- —
Context window
- Phi-3 Mini Instruct 3.8B
- 4K
- Gemini 1.0 Ultra
- Best: 33K
Reasoning
- Phi-3 Mini Instruct 3.8B
- No
- Gemini 1.0 Ultra
- No
Open weights
- Phi-3 Mini Instruct 3.8B
- Yes
- Gemini 1.0 Ultra
- No
Each reasoning level remains a separate configuration.