Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek R1 0528 (May '25)
DeepSeek
- Qwen3.5 4B (Reasoning)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek R1 0528 (May '25) DeepSeek | Qwen3.5 4B (Reasoning) Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 13.1 | 13.1 | |
| Coding | Best: 24.6 | 22.6 | |
| Math | 76 | — | |
| Agentic | 1.1 | — | |
| Speed | Best: 32.8 t/s | 19.2 t/s | |
| TTFT | 1.05 s | Best: 0.87 s | |
| Input · $ / 1M tokens | $1.35×45 relative to the lowest price among the compared models | Best: $0.030 | |
| Output · $ / 1M tokens | $3×20 relative to the lowest price among the compared models | Best: $0.15 | |
| Context window | 128K | Best: 262K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- DeepSeek R1 0528 (May '25)
- 13.1
- Qwen3.5 4B (Reasoning)
- 13.1
Coding
- DeepSeek R1 0528 (May '25)
- Best: 24.6
- Qwen3.5 4B (Reasoning)
- 22.6
Math
- DeepSeek R1 0528 (May '25)
- 76
- Qwen3.5 4B (Reasoning)
- —
Agentic
- DeepSeek R1 0528 (May '25)
- 1.1
- Qwen3.5 4B (Reasoning)
- —
Speed
- DeepSeek R1 0528 (May '25)
- Best: 32.8 t/s
- Qwen3.5 4B (Reasoning)
- 19.2 t/s
TTFT
- DeepSeek R1 0528 (May '25)
- 1.05 s
- Qwen3.5 4B (Reasoning)
- Best: 0.87 s
Input · $ / 1M tokens
- DeepSeek R1 0528 (May '25)
- $1.35×45 relative to the lowest price among the compared models
- Qwen3.5 4B (Reasoning)
- Best: $0.030
Output · $ / 1M tokens
- DeepSeek R1 0528 (May '25)
- $3×20 relative to the lowest price among the compared models
- Qwen3.5 4B (Reasoning)
- Best: $0.15
Context window
- DeepSeek R1 0528 (May '25)
- 128K
- Qwen3.5 4B (Reasoning)
- Best: 262K
Reasoning
- DeepSeek R1 0528 (May '25)
- Yes
- Qwen3.5 4B (Reasoning)
- Yes
Open weights
- DeepSeek R1 0528 (May '25)
- Yes
- Qwen3.5 4B (Reasoning)
- 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.
- DeepSeek R1 0528 (May '25)13.1 · $1.76
- Qwen3.5 4B (Reasoning)13.1 · $0.060