Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Phi-4
Microsoft
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Phi-4 Microsoft | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 5.9 | 5.9 | |
| Coding | — | 4.7 | |
| Math | 18 | — | |
| Speed | 41.4 t/s | — | |
| TTFT | 2.59 s | — | |
| Input · $ / 1M tokens | $0.125 | — | |
| Output · $ / 1M tokens | $0.50 | — | |
| Context window | 16K | Best: 131K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Phi-4
- 5.9
- Granite 4.1 3B
- 5.9
Coding
- Phi-4
- —
- Granite 4.1 3B
- 4.7
Math
- Phi-4
- 18
- Granite 4.1 3B
- —
Speed
- Phi-4
- 41.4 t/s
- Granite 4.1 3B
- —
TTFT
- Phi-4
- 2.59 s
- Granite 4.1 3B
- —
Input · $ / 1M tokens
- Phi-4
- $0.125
- Granite 4.1 3B
- —
Output · $ / 1M tokens
- Phi-4
- $0.50
- Granite 4.1 3B
- —
Context window
- Phi-4
- 16K
- Granite 4.1 3B
- Best: 131K
Reasoning
- Phi-4
- No
- Granite 4.1 3B
- No
Open weights
- Phi-4
- Yes
- Granite 4.1 3B
- Yes
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- Phi-45.9 · $0.219
Not plotted for lack of data on these axes: Granite 4.1 3B.