Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V4 Pro 0424 (Max)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V4 Pro 0424 (Max) DeepSeek | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | Best: 30.9 | 30.4 | |
| Coding | — | 59.4 | |
| Agentic | — | 26.3 | |
| Speed | 54 t/s | Best: 91.3 t/s | |
| TTFT | Best: 1.37 s | 1.82 s | |
| Input · $ / 1M tokens | $5×11.5 relative to the lowest price among the compared models | Best: $0.435 | |
| Output · $ / 1M tokens | $25×28.7 relative to the lowest price among the compared models | Best: $0.87 | |
| Context window | 1M | 1M | |
| Reasoning | No | Yes | |
| Open weights | No | Yes | |
| Cost / task | — | $0.122 |
Intelligence
- Claude Opus 4.7 (Non-reasoning, High)
- Best: 30.9
- DeepSeek V4 Pro 0424 (Max)
- 30.4
Coding
- Claude Opus 4.7 (Non-reasoning, High)
- —
- DeepSeek V4 Pro 0424 (Max)
- 59.4
Agentic
- Claude Opus 4.7 (Non-reasoning, High)
- —
- DeepSeek V4 Pro 0424 (Max)
- 26.3
Speed
- Claude Opus 4.7 (Non-reasoning, High)
- 54 t/s
- DeepSeek V4 Pro 0424 (Max)
- Best: 91.3 t/s
TTFT
- Claude Opus 4.7 (Non-reasoning, High)
- Best: 1.37 s
- DeepSeek V4 Pro 0424 (Max)
- 1.82 s
Input · $ / 1M tokens
- Claude Opus 4.7 (Non-reasoning, High)
- $5×11.5 relative to the lowest price among the compared models
- DeepSeek V4 Pro 0424 (Max)
- Best: $0.435
Output · $ / 1M tokens
- Claude Opus 4.7 (Non-reasoning, High)
- $25×28.7 relative to the lowest price among the compared models
- DeepSeek V4 Pro 0424 (Max)
- Best: $0.87
Context window
- Claude Opus 4.7 (Non-reasoning, High)
- 1M
- DeepSeek V4 Pro 0424 (Max)
- 1M
Reasoning
- Claude Opus 4.7 (Non-reasoning, High)
- No
- DeepSeek V4 Pro 0424 (Max)
- Yes
Open weights
- Claude Opus 4.7 (Non-reasoning, High)
- No
- DeepSeek V4 Pro 0424 (Max)
- Yes
Cost / task
- Claude Opus 4.7 (Non-reasoning, High)
- —
- 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.
- Claude Opus 4.7 (Non-reasoning, High)30.9 · $10
- DeepSeek V4 Pro 0424 (Max)30.4 · $0.544