Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3.5 4B (Reasoning)
Alibaba
- DeepSeek R1 0528 (May '25)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3.5 4B (Reasoning) Alibaba | DeepSeek R1 0528 (May '25) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 13.1 | 13.1 | |
| Coding | 22.6 | Best: 24.6 | |
| Math | — | 76 | |
| Agentic | — | 1.1 | |
| Speed | 19.2 t/s | Best: 33.9 t/s | |
| TTFT | Best: 0.87 s | 1.03 s | |
| Input · $ / 1M tokens | Best: $0.030 | $1.35×45 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.15 | $3×20 relative to the lowest price among the compared models | |
| Context window | Best: 262K | 128K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- Qwen3.5 4B (Reasoning)
- 13.1
- DeepSeek R1 0528 (May '25)
- 13.1
Coding
- Qwen3.5 4B (Reasoning)
- 22.6
- DeepSeek R1 0528 (May '25)
- Best: 24.6
Math
- Qwen3.5 4B (Reasoning)
- —
- DeepSeek R1 0528 (May '25)
- 76
Agentic
- Qwen3.5 4B (Reasoning)
- —
- DeepSeek R1 0528 (May '25)
- 1.1
Speed
- Qwen3.5 4B (Reasoning)
- 19.2 t/s
- DeepSeek R1 0528 (May '25)
- Best: 33.9 t/s
TTFT
- Qwen3.5 4B (Reasoning)
- Best: 0.87 s
- DeepSeek R1 0528 (May '25)
- 1.03 s
Input · $ / 1M tokens
- Qwen3.5 4B (Reasoning)
- Best: $0.030
- DeepSeek R1 0528 (May '25)
- $1.35×45 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Qwen3.5 4B (Reasoning)
- Best: $0.15
- DeepSeek R1 0528 (May '25)
- $3×20 relative to the lowest price among the compared models
Context window
- Qwen3.5 4B (Reasoning)
- Best: 262K
- DeepSeek R1 0528 (May '25)
- 128K
Reasoning
- Qwen3.5 4B (Reasoning)
- Yes
- DeepSeek R1 0528 (May '25)
- Yes
Open weights
- Qwen3.5 4B (Reasoning)
- Yes
- DeepSeek R1 0528 (May '25)
- 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.
- Qwen3.5 4B (Reasoning)13.1 · $0.060
- DeepSeek R1 0528 (May '25)13.1 · $1.76