Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Kimi K2.5 (Reasoning)
Moonshot AI
- DeepSeek V4 Pro 0813 (Max)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Kimi K2.5 (Reasoning) Moonshot AI | DeepSeek V4 Pro 0813 (Max) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 23.5 | 23.1 | |
| Coding | 46.8 | Best: 68.8 | |
| Agentic | — | 41.3 | |
| Speed | 49.8 t/s | Best: 72.7 t/s | |
| TTFT | 1.96 s | Best: 1.62 s | |
| Input · $ / 1M tokens | Best: $0.60 | $1.32×2.2 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $3 | $3.96×1.3 relative to the lowest price among the compared models | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | — | $1.77 |
Intelligence
- Kimi K2.5 (Reasoning)
- Best: 23.5
- DeepSeek V4 Pro 0813 (Max)
- 23.1
Coding
- Kimi K2.5 (Reasoning)
- 46.8
- DeepSeek V4 Pro 0813 (Max)
- Best: 68.8
Agentic
- Kimi K2.5 (Reasoning)
- —
- DeepSeek V4 Pro 0813 (Max)
- 41.3
Speed
- Kimi K2.5 (Reasoning)
- 49.8 t/s
- DeepSeek V4 Pro 0813 (Max)
- Best: 72.7 t/s
TTFT
- Kimi K2.5 (Reasoning)
- 1.96 s
- DeepSeek V4 Pro 0813 (Max)
- Best: 1.62 s
Input · $ / 1M tokens
- Kimi K2.5 (Reasoning)
- Best: $0.60
- DeepSeek V4 Pro 0813 (Max)
- $1.32×2.2 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Kimi K2.5 (Reasoning)
- Best: $3
- DeepSeek V4 Pro 0813 (Max)
- $3.96×1.3 relative to the lowest price among the compared models
Context window
- Kimi K2.5 (Reasoning)
- 1M
- DeepSeek V4 Pro 0813 (Max)
- 1M
Reasoning
- Kimi K2.5 (Reasoning)
- Yes
- DeepSeek V4 Pro 0813 (Max)
- Yes
Open weights
- Kimi K2.5 (Reasoning)
- Yes
- DeepSeek V4 Pro 0813 (Max)
- Yes
Cost / task
- Kimi K2.5 (Reasoning)
- —
- DeepSeek V4 Pro 0813 (Max)
- $1.77
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.
- Kimi K2.5 (Reasoning)23.5 · $1.20
- DeepSeek V4 Pro 0813 (Max)23.1 · $1.98