Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Sonnet 5 (Xhigh)
Anthropic
- DeepSeek V4 Flash Vision (Max)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Sonnet 5 (Xhigh) Anthropic | DeepSeek V4 Flash Vision (Max) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 34.4 | Best: 34.8 | |
| Coding | — | 65 | |
| Agentic | — | 47.5 | |
| Speed | 61.9 t/s | Best: 173 t/s | |
| TTFT | 37.4 s | Best: 1.18 s | |
| Input · $ / 1M tokens | $2×4.5 relative to the lowest price among the compared models | Best: $0.44 | |
| Output · $ / 1M tokens | $10×7.6 relative to the lowest price among the compared models | Best: $1.32 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | $2.87×9.1 relative to the lowest price among the compared models | Best: $0.314 |
Intelligence
- Claude Sonnet 5 (Xhigh)
- 34.4
- DeepSeek V4 Flash Vision (Max)
- Best: 34.8
Coding
- Claude Sonnet 5 (Xhigh)
- —
- DeepSeek V4 Flash Vision (Max)
- 65
Agentic
- Claude Sonnet 5 (Xhigh)
- —
- DeepSeek V4 Flash Vision (Max)
- 47.5
Speed
- Claude Sonnet 5 (Xhigh)
- 61.9 t/s
- DeepSeek V4 Flash Vision (Max)
- Best: 173 t/s
TTFT
- Claude Sonnet 5 (Xhigh)
- 37.4 s
- DeepSeek V4 Flash Vision (Max)
- Best: 1.18 s
Input · $ / 1M tokens
- Claude Sonnet 5 (Xhigh)
- $2×4.5 relative to the lowest price among the compared models
- DeepSeek V4 Flash Vision (Max)
- Best: $0.44
Output · $ / 1M tokens
- Claude Sonnet 5 (Xhigh)
- $10×7.6 relative to the lowest price among the compared models
- DeepSeek V4 Flash Vision (Max)
- Best: $1.32
Context window
- Claude Sonnet 5 (Xhigh)
- 1M
- DeepSeek V4 Flash Vision (Max)
- 1M
Reasoning
- Claude Sonnet 5 (Xhigh)
- Yes
- DeepSeek V4 Flash Vision (Max)
- Yes
Open weights
- Claude Sonnet 5 (Xhigh)
- No
- DeepSeek V4 Flash Vision (Max)
- No
Cost / task
- Claude Sonnet 5 (Xhigh)
- $2.87×9.1 relative to the lowest price among the compared models
- DeepSeek V4 Flash Vision (Max)
- Best: $0.314
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 Sonnet 5 (Xhigh)34.4 · $2.87
- DeepSeek V4 Flash Vision (Max)34.8 · $0.314