Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Haiku 5.5 (Max)
Anthropic
- Kimi K3 (Max)
Moonshot AI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Haiku 5.5 (Max) Anthropic | Kimi K3 (Max) Moonshot AI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 43.4 | Best: 43.6 | |
| Coding | — | 76.2 | |
| Agentic | — | 50 | |
| Cyber Index | — | 41.3% | |
| Speed | Best: 236 t/s | 43.3 t/s | |
| TTFT | 337 s | Best: 3.35 s | |
| Input · $ / 1M tokens | Best: $0.10 | $3×30 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.50 | $15×30 relative to the lowest price among the compared models | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $0.213 | $2.00×9.4 relative to the lowest price among the compared models |
Intelligence
- Claude Haiku 5.5 (Max)
- 43.4
- Kimi K3 (Max)
- Best: 43.6
Coding
- Claude Haiku 5.5 (Max)
- —
- Kimi K3 (Max)
- 76.2
Agentic
- Claude Haiku 5.5 (Max)
- —
- Kimi K3 (Max)
- 50
Cyber Index
- Claude Haiku 5.5 (Max)
- —
- Kimi K3 (Max)
- 41.3%
Speed
- Claude Haiku 5.5 (Max)
- Best: 236 t/s
- Kimi K3 (Max)
- 43.3 t/s
TTFT
- Claude Haiku 5.5 (Max)
- 337 s
- Kimi K3 (Max)
- Best: 3.35 s
Input · $ / 1M tokens
- Claude Haiku 5.5 (Max)
- Best: $0.10
- Kimi K3 (Max)
- $3×30 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Claude Haiku 5.5 (Max)
- Best: $0.50
- Kimi K3 (Max)
- $15×30 relative to the lowest price among the compared models
Context window
- Claude Haiku 5.5 (Max)
- 1M
- Kimi K3 (Max)
- 1M
Reasoning
- Claude Haiku 5.5 (Max)
- Yes
- Kimi K3 (Max)
- Yes
Open weights
- Claude Haiku 5.5 (Max)
- No
- Kimi K3 (Max)
- No
Cost / task
- Claude Haiku 5.5 (Max)
- Best: $0.213
- Kimi K3 (Max)
- $2.00×9.4 relative to the lowest price among the compared models
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 (Max)43.4 · $0.213
- Kimi K3 (Max)43.6 · $2.00