Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Tri-21B-think Preview
Trillion Labs
- DeepSeek V3 0324
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Tri-21B-think Preview Trillion Labs | DeepSeek V3 0324 DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 9.6 | Best: 9.7 | |
| Coding | — | 21.2 | |
| Math | — | 41 | |
| Agentic | — | 0.8 | |
| Speed | — | 83.5 t/s | |
| TTFT | — | 0.71 s | |
| Input · $ / 1M tokens | — | $0.24 | |
| Output · $ / 1M tokens | — | $0.90 | |
| Context window | 32K | Best: 128K | |
| Reasoning | Yes | No | |
| Open weights | Yes | Yes | |
| Cost / task | — | $0.0211 |
Intelligence
- Tri-21B-think Preview
- 9.6
- DeepSeek V3 0324
- Best: 9.7
Coding
- Tri-21B-think Preview
- —
- DeepSeek V3 0324
- 21.2
Math
- Tri-21B-think Preview
- —
- DeepSeek V3 0324
- 41
Agentic
- Tri-21B-think Preview
- —
- DeepSeek V3 0324
- 0.8
Speed
- Tri-21B-think Preview
- —
- DeepSeek V3 0324
- 83.5 t/s
TTFT
- Tri-21B-think Preview
- —
- DeepSeek V3 0324
- 0.71 s
Input · $ / 1M tokens
- Tri-21B-think Preview
- —
- DeepSeek V3 0324
- $0.24
Output · $ / 1M tokens
- Tri-21B-think Preview
- —
- DeepSeek V3 0324
- $0.90
Context window
- Tri-21B-think Preview
- 32K
- DeepSeek V3 0324
- Best: 128K
Reasoning
- Tri-21B-think Preview
- Yes
- DeepSeek V3 0324
- No
Open weights
- Tri-21B-think Preview
- Yes
- DeepSeek V3 0324
- Yes
Cost / task
- Tri-21B-think Preview
- —
- DeepSeek V3 0324
- $0.0211
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.
- DeepSeek V3 03249.7 · $0.0211
Not plotted for lack of data on these axes: Tri-21B-think Preview.