Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V4 Pro 0813 (Max)
DeepSeek
- GPT-5.6 Luna (Max)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V4 Pro 0813 (Max) DeepSeek | GPT-5.6 Luna (Max) OpenAI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 36 | Best: 37.3 | |
| Coding | 68.8 | Best: 71.4 | |
| Agentic | 41.3 | Best: 42.1 | |
| Speed | 92 t/s | Best: 115 t/s | |
| TTFT | Best: 1.71 s | 121 s | |
| Input · $ / 1M tokens | $1.32×6.6 relative to the lowest price among the compared models | Best: $0.20 | |
| Output · $ / 1M tokens | $3.96×3.3 relative to the lowest price among the compared models | Best: $1.20 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No | |
| Cost / task | $0.674×3.8 relative to the lowest price among the compared models | Best: $0.178 |
Intelligence
- DeepSeek V4 Pro 0813 (Max)
- 36
- GPT-5.6 Luna (Max)
- Best: 37.3
Coding
- DeepSeek V4 Pro 0813 (Max)
- 68.8
- GPT-5.6 Luna (Max)
- Best: 71.4
Agentic
- DeepSeek V4 Pro 0813 (Max)
- 41.3
- GPT-5.6 Luna (Max)
- Best: 42.1
Speed
- DeepSeek V4 Pro 0813 (Max)
- 92 t/s
- GPT-5.6 Luna (Max)
- Best: 115 t/s
TTFT
- DeepSeek V4 Pro 0813 (Max)
- Best: 1.71 s
- GPT-5.6 Luna (Max)
- 121 s
Input · $ / 1M tokens
- DeepSeek V4 Pro 0813 (Max)
- $1.32×6.6 relative to the lowest price among the compared models
- GPT-5.6 Luna (Max)
- Best: $0.20
Output · $ / 1M tokens
- DeepSeek V4 Pro 0813 (Max)
- $3.96×3.3 relative to the lowest price among the compared models
- GPT-5.6 Luna (Max)
- Best: $1.20
Context window
- DeepSeek V4 Pro 0813 (Max)
- 1M
- GPT-5.6 Luna (Max)
- 1M
Reasoning
- DeepSeek V4 Pro 0813 (Max)
- Yes
- GPT-5.6 Luna (Max)
- Yes
Open weights
- DeepSeek V4 Pro 0813 (Max)
- Yes
- GPT-5.6 Luna (Max)
- No
Cost / task
- DeepSeek V4 Pro 0813 (Max)
- $0.674×3.8 relative to the lowest price among the compared models
- GPT-5.6 Luna (Max)
- Best: $0.178
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 Pro 0813 (Max)36 · $0.674
- GPT-5.6 Luna (Max)37.3 · $0.178