Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.2 (Xhigh)
OpenAI
- DeepSeek V4 Pro 0424 (Max)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.2 (Xhigh) OpenAI | DeepSeek V4 Pro 0424 (Max) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 30.4 | 30.4 | |
| Coding | — | 59.4 | |
| Math | 99 | — | |
| Agentic | — | 26.3 | |
| Speed | 73.3 t/s | Best: 83.4 t/s | |
| TTFT | 108 s | Best: 1.8 s | |
| Input · $ / 1M tokens | $1.75×4 relative to the lowest price among the compared models | Best: $0.435 | |
| Output · $ / 1M tokens | $14×16.1 relative to the lowest price among the compared models | Best: $0.87 | |
| Context window | 400K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | — | $0.122 |
Intelligence
- GPT-5.2 (Xhigh)
- 30.4
- DeepSeek V4 Pro 0424 (Max)
- 30.4
Coding
- GPT-5.2 (Xhigh)
- —
- DeepSeek V4 Pro 0424 (Max)
- 59.4
Math
- GPT-5.2 (Xhigh)
- 99
- DeepSeek V4 Pro 0424 (Max)
- —
Agentic
- GPT-5.2 (Xhigh)
- —
- DeepSeek V4 Pro 0424 (Max)
- 26.3
Speed
- GPT-5.2 (Xhigh)
- 73.3 t/s
- DeepSeek V4 Pro 0424 (Max)
- Best: 83.4 t/s
TTFT
- GPT-5.2 (Xhigh)
- 108 s
- DeepSeek V4 Pro 0424 (Max)
- Best: 1.8 s
Input · $ / 1M tokens
- GPT-5.2 (Xhigh)
- $1.75×4 relative to the lowest price among the compared models
- DeepSeek V4 Pro 0424 (Max)
- Best: $0.435
Output · $ / 1M tokens
- GPT-5.2 (Xhigh)
- $14×16.1 relative to the lowest price among the compared models
- DeepSeek V4 Pro 0424 (Max)
- Best: $0.87
Context window
- GPT-5.2 (Xhigh)
- 400K
- DeepSeek V4 Pro 0424 (Max)
- Best: 1M
Reasoning
- GPT-5.2 (Xhigh)
- Yes
- DeepSeek V4 Pro 0424 (Max)
- Yes
Open weights
- GPT-5.2 (Xhigh)
- No
- DeepSeek V4 Pro 0424 (Max)
- Yes
Cost / task
- GPT-5.2 (Xhigh)
- —
- DeepSeek V4 Pro 0424 (Max)
- $0.122
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.
- GPT-5.2 (Xhigh)30.4 · $4.81
- DeepSeek V4 Pro 0424 (Max)30.4 · $0.544