Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V4 Flash 0420 (High)
DeepSeek
- GPT-5.4 mini (Xhigh)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V4 Flash 0420 (High) DeepSeek | GPT-5.4 mini (Xhigh) OpenAI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 24.4 | 24.1 | |
| Coding | 52 | Best: 56.1 | |
| Agentic | Best: 26.3 | 17.9 | |
| Speed | 46 t/s | Best: 230 t/s | |
| TTFT | Best: 1.39 s | 102 s | |
| Input · $ / 1M tokens | Best: $0.112 | $0.75×6.7 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.234 | $4.50×19.2 relative to the lowest price among the compared models | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No | |
| Cost / task | Best: $0.128 | $0.371×2.9 relative to the lowest price among the compared models |
Intelligence
- DeepSeek V4 Flash 0420 (High)
- Best: 24.4
- GPT-5.4 mini (Xhigh)
- 24.1
Coding
- DeepSeek V4 Flash 0420 (High)
- 52
- GPT-5.4 mini (Xhigh)
- Best: 56.1
Agentic
- DeepSeek V4 Flash 0420 (High)
- Best: 26.3
- GPT-5.4 mini (Xhigh)
- 17.9
Speed
- DeepSeek V4 Flash 0420 (High)
- 46 t/s
- GPT-5.4 mini (Xhigh)
- Best: 230 t/s
TTFT
- DeepSeek V4 Flash 0420 (High)
- Best: 1.39 s
- GPT-5.4 mini (Xhigh)
- 102 s
Input · $ / 1M tokens
- DeepSeek V4 Flash 0420 (High)
- Best: $0.112
- GPT-5.4 mini (Xhigh)
- $0.75×6.7 relative to the lowest price among the compared models
Output · $ / 1M tokens
- DeepSeek V4 Flash 0420 (High)
- Best: $0.234
- GPT-5.4 mini (Xhigh)
- $4.50×19.2 relative to the lowest price among the compared models
Context window
- DeepSeek V4 Flash 0420 (High)
- 1M
- GPT-5.4 mini (Xhigh)
- 1M
Reasoning
- DeepSeek V4 Flash 0420 (High)
- Yes
- GPT-5.4 mini (Xhigh)
- Yes
Open weights
- DeepSeek V4 Flash 0420 (High)
- Yes
- GPT-5.4 mini (Xhigh)
- No
Cost / task
- DeepSeek V4 Flash 0420 (High)
- Best: $0.128
- GPT-5.4 mini (Xhigh)
- $0.371×2.9 relative to the lowest price among the compared models
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 Flash 0420 (High)24.4 · $0.128
- GPT-5.4 mini (Xhigh)24.1 · $0.371