Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Nova 2.0 Lite (Low)
Amazon
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Nova 2.0 Lite (Low) Amazon | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 11.8 | Best: 11.9 | |
| Math | Best: 46.7 | 39.3 | |
| Speed | Best: 183 t/s | 97.4 t/s | |
| TTFT | 10.4 s | Best: 0.92 s | |
| Input · $ / 1M tokens | $0.33×1.1 relative to the lowest price among the compared models | Best: $0.30 | |
| Output · $ / 1M tokens | $2.75×1.5 relative to the lowest price among the compared models | Best: $1.80 | |
| Context window | Best: 1M | 262K | |
| Reasoning | Yes | No | |
| Open weights | No | Yes |
Intelligence
- Nova 2.0 Lite (Low)
- 11.8
- Qwen3 Coder 480B A35B Instruct
- Best: 11.9
Math
- Nova 2.0 Lite (Low)
- Best: 46.7
- Qwen3 Coder 480B A35B Instruct
- 39.3
Speed
- Nova 2.0 Lite (Low)
- Best: 183 t/s
- Qwen3 Coder 480B A35B Instruct
- 97.4 t/s
TTFT
- Nova 2.0 Lite (Low)
- 10.4 s
- Qwen3 Coder 480B A35B Instruct
- Best: 0.92 s
Input · $ / 1M tokens
- Nova 2.0 Lite (Low)
- $0.33×1.1 relative to the lowest price among the compared models
- Qwen3 Coder 480B A35B Instruct
- Best: $0.30
Output · $ / 1M tokens
- Nova 2.0 Lite (Low)
- $2.75×1.5 relative to the lowest price among the compared models
- Qwen3 Coder 480B A35B Instruct
- Best: $1.80
Context window
- Nova 2.0 Lite (Low)
- Best: 1M
- Qwen3 Coder 480B A35B Instruct
- 262K
Reasoning
- Nova 2.0 Lite (Low)
- Yes
- Qwen3 Coder 480B A35B Instruct
- No
Open weights
- Nova 2.0 Lite (Low)
- No
- Qwen3 Coder 480B A35B Instruct
- 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.
- Nova 2.0 Lite (Low)11.8 · $0.935
- Qwen3 Coder 480B A35B Instruct11.9 · $0.675