Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 1.7B (Non-reasoning)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 1.7B (Non-reasoning) Alibaba | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 4.9 | 4.9 | |
| Math | 6.7 | Best: 7.3 | |
| Speed | 44.4 t/s | — | |
| TTFT | 9.1 s | — | |
| Input · $ / 1M tokens | $0.030 | — | |
| Output · $ / 1M tokens | $0.25 | — | |
| Context window | Best: 128K | 32K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Granite 3.3 8B (Non-reasoning)
- 4.9
- Qwen3 1.7B (Non-reasoning)
- 4.9
Math
- Granite 3.3 8B (Non-reasoning)
- 6.7
- Qwen3 1.7B (Non-reasoning)
- Best: 7.3
Speed
- Granite 3.3 8B (Non-reasoning)
- 44.4 t/s
- Qwen3 1.7B (Non-reasoning)
- —
TTFT
- Granite 3.3 8B (Non-reasoning)
- 9.1 s
- Qwen3 1.7B (Non-reasoning)
- —
Input · $ / 1M tokens
- Granite 3.3 8B (Non-reasoning)
- $0.030
- Qwen3 1.7B (Non-reasoning)
- —
Output · $ / 1M tokens
- Granite 3.3 8B (Non-reasoning)
- $0.25
- Qwen3 1.7B (Non-reasoning)
- —
Context window
- Granite 3.3 8B (Non-reasoning)
- Best: 128K
- Qwen3 1.7B (Non-reasoning)
- 32K
Reasoning
- Granite 3.3 8B (Non-reasoning)
- No
- Qwen3 1.7B (Non-reasoning)
- No
Open weights
- Granite 3.3 8B (Non-reasoning)
- Yes
- Qwen3 1.7B (Non-reasoning)
- 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.
- Granite 3.3 8B (Non-reasoning)4.9 · $0.085
Not plotted for lack of data on these axes: Qwen3 1.7B (Non-reasoning).