Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Trinity Large Thinking
Arcee AI
- 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 | Trinity Large Thinking Arcee AI | Mi:dm K 2.5 Pro Korea Telecom | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 10.8 | Best: 11 | |
| Coding | 25.8 | — | |
| Math | — | 76.7 | |
| Agentic | 1 | — | |
| Speed | 346 t/s | — | |
| TTFT | 1.1 s | — | |
| Input · $ / 1M tokens | $0.25 | — | |
| Output · $ / 1M tokens | $0.80 | — | |
| Context window | Best: 512K | 128K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No | |
| Cost / task | $0.119 | — |
Intelligence
- Trinity Large Thinking
- 10.8
- Mi:dm K 2.5 Pro
- Best: 11
Coding
- Trinity Large Thinking
- 25.8
- Mi:dm K 2.5 Pro
- —
Math
- Trinity Large Thinking
- —
- Mi:dm K 2.5 Pro
- 76.7
Agentic
- Trinity Large Thinking
- 1
- Mi:dm K 2.5 Pro
- —
Speed
- Trinity Large Thinking
- 346 t/s
- Mi:dm K 2.5 Pro
- —
TTFT
- Trinity Large Thinking
- 1.1 s
- Mi:dm K 2.5 Pro
- —
Input · $ / 1M tokens
- Trinity Large Thinking
- $0.25
- Mi:dm K 2.5 Pro
- —
Output · $ / 1M tokens
- Trinity Large Thinking
- $0.80
- Mi:dm K 2.5 Pro
- —
Context window
- Trinity Large Thinking
- Best: 512K
- Mi:dm K 2.5 Pro
- 128K
Reasoning
- Trinity Large Thinking
- Yes
- Mi:dm K 2.5 Pro
- Yes
Open weights
- Trinity Large Thinking
- Yes
- Mi:dm K 2.5 Pro
- No
Cost / task
- Trinity Large Thinking
- $0.119
- Mi:dm K 2.5 Pro
- —
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.
- Trinity Large Thinking10.8 · $0.119
Not plotted for lack of data on these axes: Mi:dm K 2.5 Pro.