Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Phi-4 Multimodal Instruct
Microsoft
- Gemini 1.0 Ultra
Google
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Phi-4 Multimodal Instruct Microsoft | Gemini 1.0 Ultra | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 5.8 | 5.8 | |
| Coding | — | 17.6 | |
| Speed | 19.4 t/s | — | |
| TTFT | 0.541 s | — | |
| Input · $ / 1M tokens | $0.080 | — | |
| Output · $ / 1M tokens | $0.32 | — | |
| Context window | Best: 128K | 33K | |
| Reasoning | No | No | |
| Open weights | Yes | No |
Intelligence
- Phi-4 Multimodal Instruct
- 5.8
- Gemini 1.0 Ultra
- 5.8
Coding
- Phi-4 Multimodal Instruct
- —
- Gemini 1.0 Ultra
- 17.6
Speed
- Phi-4 Multimodal Instruct
- 19.4 t/s
- Gemini 1.0 Ultra
- —
TTFT
- Phi-4 Multimodal Instruct
- 0.541 s
- Gemini 1.0 Ultra
- —
Input · $ / 1M tokens
- Phi-4 Multimodal Instruct
- $0.080
- Gemini 1.0 Ultra
- —
Output · $ / 1M tokens
- Phi-4 Multimodal Instruct
- $0.32
- Gemini 1.0 Ultra
- —
Context window
- Phi-4 Multimodal Instruct
- Best: 128K
- Gemini 1.0 Ultra
- 33K
Reasoning
- Phi-4 Multimodal Instruct
- No
- Gemini 1.0 Ultra
- No
Open weights
- Phi-4 Multimodal Instruct
- Yes
- Gemini 1.0 Ultra
- No
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-4 Multimodal Instruct5.8 · $0.14
Not plotted for lack of data on these axes: Gemini 1.0 Ultra.