Model Comparator
Compare up to four models using the same criteria.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | 7.7 | 7.7 | |
| Math | — | 14 | |
| Speed | — | 23.1 t/s | |
| TTFT | — | 6.5 s | |
| Input · $ / 1M tokens | — | $0.475 | |
| Output · $ / 1M tokens | — | $0.495 | |
| Context window | 65.5K | Best: 131K | |
| Reasoning | Yes | No | |
| Open weights | Yes | Yes |
Intelligence
- Step3 VL 10B
- 7.7
- Qwen2.5 Instruct 72B
- 7.7
Math
- Step3 VL 10B
- —
- Qwen2.5 Instruct 72B
- 14
Speed
- Step3 VL 10B
- —
- Qwen2.5 Instruct 72B
- 23.1 t/s
TTFT
- Step3 VL 10B
- —
- Qwen2.5 Instruct 72B
- 6.5 s
Input · $ / 1M tokens
- Step3 VL 10B
- —
- Qwen2.5 Instruct 72B
- $0.475
Output · $ / 1M tokens
- Step3 VL 10B
- —
- Qwen2.5 Instruct 72B
- $0.495
Context window
- Step3 VL 10B
- 65.5K
- Qwen2.5 Instruct 72B
- Best: 131K
Reasoning
- Step3 VL 10B
- Yes
- Qwen2.5 Instruct 72B
- No
Open weights
- Step3 VL 10B
- Yes
- Qwen2.5 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.
- Qwen2.5 Instruct 72B7.7 · $0.48
Not plotted for lack of data on these axes: Step3 VL 10B.