Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V4 Pro 0813 (Max)
DeepSeek
- Qwen3.5 27B (Reasoning)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V4 Pro 0813 (Max) DeepSeek | Qwen3.5 27B (Reasoning) Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 23.1 | 22.9 | |
| Coding | 68.8 | — | |
| Agentic | 41.3 | — | |
| Speed | 72.7 t/s | Best: 75.3 t/s | |
| TTFT | Best: 1.62 s | 5.59 s | |
| Input · $ / 1M tokens | $1.32×4.4 relative to the lowest price among the compared models | Best: $0.30 | |
| Output · $ / 1M tokens | $3.96×1.7 relative to the lowest price among the compared models | Best: $2.40 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $1.77 | — |
Intelligence
- DeepSeek V4 Pro 0813 (Max)
- Best: 23.1
- Qwen3.5 27B (Reasoning)
- 22.9
Coding
- DeepSeek V4 Pro 0813 (Max)
- 68.8
- Qwen3.5 27B (Reasoning)
- —
Agentic
- DeepSeek V4 Pro 0813 (Max)
- 41.3
- Qwen3.5 27B (Reasoning)
- —
Speed
- DeepSeek V4 Pro 0813 (Max)
- 72.7 t/s
- Qwen3.5 27B (Reasoning)
- Best: 75.3 t/s
TTFT
- DeepSeek V4 Pro 0813 (Max)
- Best: 1.62 s
- Qwen3.5 27B (Reasoning)
- 5.59 s
Input · $ / 1M tokens
- DeepSeek V4 Pro 0813 (Max)
- $1.32×4.4 relative to the lowest price among the compared models
- Qwen3.5 27B (Reasoning)
- Best: $0.30
Output · $ / 1M tokens
- DeepSeek V4 Pro 0813 (Max)
- $3.96×1.7 relative to the lowest price among the compared models
- Qwen3.5 27B (Reasoning)
- Best: $2.40
Context window
- DeepSeek V4 Pro 0813 (Max)
- 1M
- Qwen3.5 27B (Reasoning)
- 1M
Reasoning
- DeepSeek V4 Pro 0813 (Max)
- Yes
- Qwen3.5 27B (Reasoning)
- Yes
Open weights
- DeepSeek V4 Pro 0813 (Max)
- Yes
- Qwen3.5 27B (Reasoning)
- Yes
Cost / task
- DeepSeek V4 Pro 0813 (Max)
- $1.77
- Qwen3.5 27B (Reasoning)
- —
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 (Max)23.1 · $1.98
- Qwen3.5 27B (Reasoning)22.9 · $0.825