Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek-V2.5
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek-V2.5 DeepSeek | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 6.6 | 6.6 | |
| Coding | 9.5 | — | |
| Speed | 126 t/s | — | |
| TTFT | 0.75 s | — | |
| Input · $ / 1M tokens | $0.050 | — | |
| Output · $ / 1M tokens | $0.10 | — | |
| Context window | Best: 131K | 128K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Granite 4.1 8B
- 6.6
- DeepSeek-V2.5
- 6.6
Coding
- Granite 4.1 8B
- 9.5
- DeepSeek-V2.5
- —
Speed
- Granite 4.1 8B
- 126 t/s
- DeepSeek-V2.5
- —
TTFT
- Granite 4.1 8B
- 0.75 s
- DeepSeek-V2.5
- —
Input · $ / 1M tokens
- Granite 4.1 8B
- $0.050
- DeepSeek-V2.5
- —
Output · $ / 1M tokens
- Granite 4.1 8B
- $0.10
- DeepSeek-V2.5
- —
Context window
- Granite 4.1 8B
- Best: 131K
- DeepSeek-V2.5
- 128K
Reasoning
- Granite 4.1 8B
- No
- DeepSeek-V2.5
- No
Open weights
- Granite 4.1 8B
- Yes
- DeepSeek-V2.5
- Yes
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.
- Granite 4.1 8B6.6 · $0.063
Not plotted for lack of data on these axes: DeepSeek-V2.5.