Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Haiku 5.5 (Low)
Anthropic
- KAT-Coder-Pro V1
KwaiKAT
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Haiku 5.5 (Low) Anthropic | KAT-Coder-Pro V1 KwaiKAT | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 18.6 | 18.6 | |
| Math | — | 94.7 | |
| Speed | 147 t/s | — | |
| TTFT | 9.07 s | — | |
| Input · $ / 1M tokens | $0.10 | — | |
| Output · $ / 1M tokens | $0.50 | — | |
| Context window | Best: 1M | 256K | |
| Reasoning | Yes | No | |
| Open weights | No | No | |
| Cost / task | $0.0438 | — |
Intelligence
- Claude Haiku 5.5 (Low)
- 18.6
- KAT-Coder-Pro V1
- 18.6
Math
- Claude Haiku 5.5 (Low)
- —
- KAT-Coder-Pro V1
- 94.7
Speed
- Claude Haiku 5.5 (Low)
- 147 t/s
- KAT-Coder-Pro V1
- —
TTFT
- Claude Haiku 5.5 (Low)
- 9.07 s
- KAT-Coder-Pro V1
- —
Input · $ / 1M tokens
- Claude Haiku 5.5 (Low)
- $0.10
- KAT-Coder-Pro V1
- —
Output · $ / 1M tokens
- Claude Haiku 5.5 (Low)
- $0.50
- KAT-Coder-Pro V1
- —
Context window
- Claude Haiku 5.5 (Low)
- Best: 1M
- KAT-Coder-Pro V1
- 256K
Reasoning
- Claude Haiku 5.5 (Low)
- Yes
- KAT-Coder-Pro V1
- No
Open weights
- Claude Haiku 5.5 (Low)
- No
- KAT-Coder-Pro V1
- No
Cost / task
- Claude Haiku 5.5 (Low)
- $0.0438
- KAT-Coder-Pro V1
- —
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 (Low)18.6 · $0.0438
Not plotted for lack of data on these axes: KAT-Coder-Pro V1.