Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mi:dm K 2.5 Pro
Korea Telecom
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mi:dm K 2.5 Pro Korea Telecom | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 11 | Best: 11.1 | |
| Coding | — | 22.4 | |
| Math | 76.7 | — | |
| Agentic | — | 1.3 | |
| Speed | — | 118 t/s | |
| TTFT | — | 0.85 s | |
| Input · $ / 1M tokens | — | $0.060 | |
| Output · $ / 1M tokens | — | $0.25 | |
| Context window | 128K | Best: 131K | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | — | $0.0236 |
Intelligence
- Mi:dm K 2.5 Pro
- 11
- Granite 4.2 8B
- Best: 11.1
Coding
- Mi:dm K 2.5 Pro
- —
- Granite 4.2 8B
- 22.4
Math
- Mi:dm K 2.5 Pro
- 76.7
- Granite 4.2 8B
- —
Agentic
- Mi:dm K 2.5 Pro
- —
- Granite 4.2 8B
- 1.3
Speed
- Mi:dm K 2.5 Pro
- —
- Granite 4.2 8B
- 118 t/s
TTFT
- Mi:dm K 2.5 Pro
- —
- Granite 4.2 8B
- 0.85 s
Input · $ / 1M tokens
- Mi:dm K 2.5 Pro
- —
- Granite 4.2 8B
- $0.060
Output · $ / 1M tokens
- Mi:dm K 2.5 Pro
- —
- Granite 4.2 8B
- $0.25
Context window
- Mi:dm K 2.5 Pro
- 128K
- Granite 4.2 8B
- Best: 131K
Reasoning
- Mi:dm K 2.5 Pro
- Yes
- Granite 4.2 8B
- Yes
Open weights
- Mi:dm K 2.5 Pro
- No
- Granite 4.2 8B
- Yes
Cost / task
- Mi:dm K 2.5 Pro
- —
- Granite 4.2 8B
- $0.0236
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 4.2 8B11.1 · $0.0236
Not plotted for lack of data on these axes: Mi:dm K 2.5 Pro.