Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Nanbeige4.3-33B
Nanbeige
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Nanbeige4.3-33B Nanbeige | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 12.6 | Best: 20.4 | |
| Speed | 77.4 t/s | Best: 159 t/s | |
| TTFT | 1.71 s | Best: 1.46 s | |
| Input · $ / 1M tokens | $1.32 | — | |
| Output · $ / 1M tokens | $3.96 | — | |
| Context window | Best: 1M | 524K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.977 | — |
Intelligence
- DeepSeek V4 Pro 0813 (Non-reasoning)
- 12.6
- Nanbeige4.3-33B
- Best: 20.4
Speed
- DeepSeek V4 Pro 0813 (Non-reasoning)
- 77.4 t/s
- Nanbeige4.3-33B
- Best: 159 t/s
TTFT
- DeepSeek V4 Pro 0813 (Non-reasoning)
- 1.71 s
- Nanbeige4.3-33B
- Best: 1.46 s
Input · $ / 1M tokens
- DeepSeek V4 Pro 0813 (Non-reasoning)
- $1.32
- Nanbeige4.3-33B
- —
Output · $ / 1M tokens
- DeepSeek V4 Pro 0813 (Non-reasoning)
- $3.96
- Nanbeige4.3-33B
- —
Context window
- DeepSeek V4 Pro 0813 (Non-reasoning)
- Best: 1M
- Nanbeige4.3-33B
- 524K
Reasoning
- DeepSeek V4 Pro 0813 (Non-reasoning)
- No
- Nanbeige4.3-33B
- Yes
Open weights
- DeepSeek V4 Pro 0813 (Non-reasoning)
- Yes
- Nanbeige4.3-33B
- Yes
Cost / task
- DeepSeek V4 Pro 0813 (Non-reasoning)
- $0.977
- Nanbeige4.3-33B
- —
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.
- DeepSeek V4 Pro 0813 (Non-reasoning)12.6 · 77.4 t/s
- Nanbeige4.3-33B20.4 · 159 t/s