Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen2.5 Instruct 72B
Alibaba
- Sonar
Perplexity
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen2.5 Instruct 72B Alibaba | Sonar Perplexity | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 7.7 | 7.7 | |
| Math | 14 | — | |
| Speed | 30.9 t/s | — | |
| TTFT | 3.92 s | — | |
| Input · $ / 1M tokens | $0.475 | — | |
| Output · $ / 1M tokens | $0.495 | — | |
| Context window | Best: 131K | 127K | |
| Reasoning | No | No | |
| Open weights | Yes | No |
Intelligence
- Qwen2.5 Instruct 72B
- 7.7
- Sonar
- 7.7
Math
- Qwen2.5 Instruct 72B
- 14
- Sonar
- —
Speed
- Qwen2.5 Instruct 72B
- 30.9 t/s
- Sonar
- —
TTFT
- Qwen2.5 Instruct 72B
- 3.92 s
- Sonar
- —
Input · $ / 1M tokens
- Qwen2.5 Instruct 72B
- $0.475
- Sonar
- —
Output · $ / 1M tokens
- Qwen2.5 Instruct 72B
- $0.495
- Sonar
- —
Context window
- Qwen2.5 Instruct 72B
- Best: 131K
- Sonar
- 127K
Reasoning
- Qwen2.5 Instruct 72B
- No
- Sonar
- No
Open weights
- Qwen2.5 Instruct 72B
- Yes
- Sonar
- 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.
- Qwen2.5 Instruct 72B7.7 · $0.48
Not plotted for lack of data on these axes: Sonar.