Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.5 (High)
OpenAI
- DeepSeek V4 Pro 0813 (Max)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.5 (High) OpenAI | DeepSeek V4 Pro 0813 (Max) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 37 | 36 | |
| Coding | Best: 71.6 | 68.8 | |
| Agentic | 34.3 | Best: 41.3 | |
| Speed | 82.7 t/s | Best: 92 t/s | |
| TTFT | 33.6 s | Best: 1.71 s | |
| Input · $ / 1M tokens | $5×3.8 relative to the lowest price among the compared models | Best: $1.32 | |
| Output · $ / 1M tokens | $30×7.6 relative to the lowest price among the compared models | Best: $3.96 | |
| Context window | 922K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | $1.54×2.3 relative to the lowest price among the compared models | Best: $0.674 |
Intelligence
- GPT-5.5 (High)
- Best: 37
- DeepSeek V4 Pro 0813 (Max)
- 36
Coding
- GPT-5.5 (High)
- Best: 71.6
- DeepSeek V4 Pro 0813 (Max)
- 68.8
Agentic
- GPT-5.5 (High)
- 34.3
- DeepSeek V4 Pro 0813 (Max)
- Best: 41.3
Speed
- GPT-5.5 (High)
- 82.7 t/s
- DeepSeek V4 Pro 0813 (Max)
- Best: 92 t/s
TTFT
- GPT-5.5 (High)
- 33.6 s
- DeepSeek V4 Pro 0813 (Max)
- Best: 1.71 s
Input · $ / 1M tokens
- GPT-5.5 (High)
- $5×3.8 relative to the lowest price among the compared models
- DeepSeek V4 Pro 0813 (Max)
- Best: $1.32
Output · $ / 1M tokens
- GPT-5.5 (High)
- $30×7.6 relative to the lowest price among the compared models
- DeepSeek V4 Pro 0813 (Max)
- Best: $3.96
Context window
- GPT-5.5 (High)
- 922K
- DeepSeek V4 Pro 0813 (Max)
- Best: 1M
Reasoning
- GPT-5.5 (High)
- Yes
- DeepSeek V4 Pro 0813 (Max)
- Yes
Open weights
- GPT-5.5 (High)
- No
- DeepSeek V4 Pro 0813 (Max)
- Yes
Cost / task
- GPT-5.5 (High)
- $1.54×2.3 relative to the lowest price among the compared models
- DeepSeek V4 Pro 0813 (Max)
- Best: $0.674
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-5.5 (High)37 · $1.54
- DeepSeek V4 Pro 0813 (Max)36 · $0.674