Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Tri-21B-Think
Trillion Labs
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Tri-21B-Think Trillion Labs | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 9 | Best: 9.1 | |
| Coding | — | 17.5 | |
| Agentic | — | 0.9 | |
| Speed | — | 220 t/s | |
| TTFT | — | 0.52 s | |
| Input · $ / 1M tokens | — | $0.030 | |
| Output · $ / 1M tokens | — | $0.12 | |
| Context window | 32K | Best: 131K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | — | $0.0060 |
Intelligence
- Tri-21B-Think
- 9
- Granite 4.2 3B
- Best: 9.1
Coding
- Tri-21B-Think
- —
- Granite 4.2 3B
- 17.5
Agentic
- Tri-21B-Think
- —
- Granite 4.2 3B
- 0.9
Speed
- Tri-21B-Think
- —
- Granite 4.2 3B
- 220 t/s
TTFT
- Tri-21B-Think
- —
- Granite 4.2 3B
- 0.52 s
Input · $ / 1M tokens
- Tri-21B-Think
- —
- Granite 4.2 3B
- $0.030
Output · $ / 1M tokens
- Tri-21B-Think
- —
- Granite 4.2 3B
- $0.12
Context window
- Tri-21B-Think
- 32K
- Granite 4.2 3B
- Best: 131K
Reasoning
- Tri-21B-Think
- Yes
- Granite 4.2 3B
- Yes
Open weights
- Tri-21B-Think
- Yes
- Granite 4.2 3B
- Yes
Cost / task
- Tri-21B-Think
- —
- Granite 4.2 3B
- $0.0060
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 3B9.1 · $0.0060
Not plotted for lack of data on these axes: Tri-21B-Think.