Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 14B (Non-reasoning)
Alibaba
- Nova Lite
Amazon
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 14B (Non-reasoning) Alibaba | Nova Lite Amazon | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 6.7 | 6.7 | |
| Math | Best: 58 | 7 | |
| Speed | 26 t/s | Best: 171 t/s | |
| TTFT | 1.17 s | Best: 0.88 s | |
| Input · $ / 1M tokens | $0.12×2 relative to the lowest price among the compared models | Best: $0.060 | |
| Output · $ / 1M tokens | $0.24 | $0.24 | |
| Context window | 1M | 1M | |
| Reasoning | No | No | |
| Open weights | Yes | No |
Intelligence
- Qwen3 14B (Non-reasoning)
- 6.7
- Nova Lite
- 6.7
Math
- Qwen3 14B (Non-reasoning)
- Best: 58
- Nova Lite
- 7
Speed
- Qwen3 14B (Non-reasoning)
- 26 t/s
- Nova Lite
- Best: 171 t/s
TTFT
- Qwen3 14B (Non-reasoning)
- 1.17 s
- Nova Lite
- Best: 0.88 s
Input · $ / 1M tokens
- Qwen3 14B (Non-reasoning)
- $0.12×2 relative to the lowest price among the compared models
- Nova Lite
- Best: $0.060
Output · $ / 1M tokens
- Qwen3 14B (Non-reasoning)
- $0.24
- Nova Lite
- $0.24
Context window
- Qwen3 14B (Non-reasoning)
- 1M
- Nova Lite
- 1M
Reasoning
- Qwen3 14B (Non-reasoning)
- No
- Nova Lite
- No
Open weights
- Qwen3 14B (Non-reasoning)
- Yes
- Nova Lite
- 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.
- Qwen3 14B (Non-reasoning)6.7 · $0.15
- Nova Lite6.7 · $0.105