Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Phi-4 Mini Instruct
Microsoft
- Qwen2 Instruct 72B
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Phi-4 Mini Instruct Microsoft | Qwen2 Instruct 72B Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 6.3 | 6.3 | |
| Coding | 3.8 | — | |
| Math | 6.7 | — | |
| Speed | 46.1 t/s | — | |
| TTFT | 0.82 s | — | |
| Input · $ / 1M tokens | $0.075 | — | |
| Output · $ / 1M tokens | $0.30 | — | |
| Context window | 128K | Best: 131K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Phi-4 Mini Instruct
- 6.3
- Qwen2 Instruct 72B
- 6.3
Coding
- Phi-4 Mini Instruct
- 3.8
- Qwen2 Instruct 72B
- —
Math
- Phi-4 Mini Instruct
- 6.7
- Qwen2 Instruct 72B
- —
Speed
- Phi-4 Mini Instruct
- 46.1 t/s
- Qwen2 Instruct 72B
- —
TTFT
- Phi-4 Mini Instruct
- 0.82 s
- Qwen2 Instruct 72B
- —
Input · $ / 1M tokens
- Phi-4 Mini Instruct
- $0.075
- Qwen2 Instruct 72B
- —
Output · $ / 1M tokens
- Phi-4 Mini Instruct
- $0.30
- Qwen2 Instruct 72B
- —
Context window
- Phi-4 Mini Instruct
- 128K
- Qwen2 Instruct 72B
- Best: 131K
Reasoning
- Phi-4 Mini Instruct
- No
- Qwen2 Instruct 72B
- No
Open weights
- Phi-4 Mini Instruct
- Yes
- Qwen2 Instruct 72B
- 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-4 Mini Instruct6.3 · $0.131
Not plotted for lack of data on these axes: Qwen2 Instruct 72B.