Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Haiku 5.5 (Xhigh)
Anthropic
- DeepSeek V4 Flash 0731 (Max)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Haiku 5.5 (Xhigh) Anthropic | DeepSeek V4 Flash 0731 (Max) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 34.6 | 34.3 | |
| Coding | — | 69.1 | |
| Agentic | — | 41 | |
| Speed | Best: 180 t/s | 129 t/s | |
| TTFT | 66.3 s | Best: 1.6 s | |
| Input · $ / 1M tokens | Best: $0.10 | $0.14×1.4 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | $0.50×1.8 relative to the lowest price among the compared models | Best: $0.28 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | $0.248×1.4 relative to the lowest price among the compared models | Best: $0.178 |
Intelligence
- Claude Haiku 5.5 (Xhigh)
- Best: 34.6
- DeepSeek V4 Flash 0731 (Max)
- 34.3
Coding
- Claude Haiku 5.5 (Xhigh)
- —
- DeepSeek V4 Flash 0731 (Max)
- 69.1
Agentic
- Claude Haiku 5.5 (Xhigh)
- —
- DeepSeek V4 Flash 0731 (Max)
- 41
Speed
- Claude Haiku 5.5 (Xhigh)
- Best: 180 t/s
- DeepSeek V4 Flash 0731 (Max)
- 129 t/s
TTFT
- Claude Haiku 5.5 (Xhigh)
- 66.3 s
- DeepSeek V4 Flash 0731 (Max)
- Best: 1.6 s
Input · $ / 1M tokens
- Claude Haiku 5.5 (Xhigh)
- Best: $0.10
- DeepSeek V4 Flash 0731 (Max)
- $0.14×1.4 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Claude Haiku 5.5 (Xhigh)
- $0.50×1.8 relative to the lowest price among the compared models
- DeepSeek V4 Flash 0731 (Max)
- Best: $0.28
Context window
- Claude Haiku 5.5 (Xhigh)
- 1M
- DeepSeek V4 Flash 0731 (Max)
- 1M
Reasoning
- Claude Haiku 5.5 (Xhigh)
- Yes
- DeepSeek V4 Flash 0731 (Max)
- Yes
Open weights
- Claude Haiku 5.5 (Xhigh)
- No
- DeepSeek V4 Flash 0731 (Max)
- Yes
Cost / task
- Claude Haiku 5.5 (Xhigh)
- $0.248×1.4 relative to the lowest price among the compared models
- DeepSeek V4 Flash 0731 (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.
- Claude Haiku 5.5 (Xhigh)34.6 · $0.248
- DeepSeek V4 Flash 0731 (Max)34.3 · $0.178