Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V4 Pro 0813 (Max)
DeepSeek
- Claude 4.1 Opus (Non-reasoning)
Anthropic
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V4 Pro 0813 (Max) DeepSeek | Claude 4.1 Opus (Non-reasoning) Anthropic | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 23.1 | 22.8 | |
| Coding | 68.8 | — | |
| Agentic | 41.3 | — | |
| Speed | 72.7 t/s | — | |
| TTFT | 1.62 s | — | |
| Input · $ / 1M tokens | Best: $1.32 | $15×11.4 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $3.96 | $75×18.9 relative to the lowest price among the compared models | |
| Context window | 1M | 1M | |
| Reasoning | Yes | No | |
| Open weights | Yes | No | |
| Cost / task | $1.77 | — |
Intelligence
- DeepSeek V4 Pro 0813 (Max)
- Best: 23.1
- Claude 4.1 Opus (Non-reasoning)
- 22.8
Coding
- DeepSeek V4 Pro 0813 (Max)
- 68.8
- Claude 4.1 Opus (Non-reasoning)
- —
Agentic
- DeepSeek V4 Pro 0813 (Max)
- 41.3
- Claude 4.1 Opus (Non-reasoning)
- —
Speed
- DeepSeek V4 Pro 0813 (Max)
- 72.7 t/s
- Claude 4.1 Opus (Non-reasoning)
- —
TTFT
- DeepSeek V4 Pro 0813 (Max)
- 1.62 s
- Claude 4.1 Opus (Non-reasoning)
- —
Input · $ / 1M tokens
- DeepSeek V4 Pro 0813 (Max)
- Best: $1.32
- Claude 4.1 Opus (Non-reasoning)
- $15×11.4 relative to the lowest price among the compared models
Output · $ / 1M tokens
- DeepSeek V4 Pro 0813 (Max)
- Best: $3.96
- Claude 4.1 Opus (Non-reasoning)
- $75×18.9 relative to the lowest price among the compared models
Context window
- DeepSeek V4 Pro 0813 (Max)
- 1M
- Claude 4.1 Opus (Non-reasoning)
- 1M
Reasoning
- DeepSeek V4 Pro 0813 (Max)
- Yes
- Claude 4.1 Opus (Non-reasoning)
- No
Open weights
- DeepSeek V4 Pro 0813 (Max)
- Yes
- Claude 4.1 Opus (Non-reasoning)
- No
Cost / task
- DeepSeek V4 Pro 0813 (Max)
- $1.77
- Claude 4.1 Opus (Non-reasoning)
- —
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)23.1 · $1.98
- Claude 4.1 Opus (Non-reasoning)22.8 · $30