Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral Medium 3
Mistral
- Tri-21B-Think
Trillion Labs
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral Medium 3 Mistral | Tri-21B-Think Trillion Labs | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 9 | 9 | |
| Math | 30.3 | — | |
| Speed | 45.1 t/s | — | |
| TTFT | 2.24 s | — | |
| Input · $ / 1M tokens | $0.40 | — | |
| Output · $ / 1M tokens | $2 | — | |
| Context window | Best: 128K | 32K | |
| Reasoning | No | Yes | |
| Open weights | No | Yes |
Intelligence
- Mistral Medium 3
- 9
- Tri-21B-Think
- 9
Math
- Mistral Medium 3
- 30.3
- Tri-21B-Think
- —
Speed
- Mistral Medium 3
- 45.1 t/s
- Tri-21B-Think
- —
TTFT
- Mistral Medium 3
- 2.24 s
- Tri-21B-Think
- —
Input · $ / 1M tokens
- Mistral Medium 3
- $0.40
- Tri-21B-Think
- —
Output · $ / 1M tokens
- Mistral Medium 3
- $2
- Tri-21B-Think
- —
Context window
- Mistral Medium 3
- Best: 128K
- Tri-21B-Think
- 32K
Reasoning
- Mistral Medium 3
- No
- Tri-21B-Think
- Yes
Open weights
- Mistral Medium 3
- No
- Tri-21B-Think
- 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.
- Mistral Medium 39 · $0.80
Not plotted for lack of data on these axes: Tri-21B-Think.