Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Mistral Medium 3.5
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Mistral Medium 3.5 Mistral | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | Best: 14.3 | 14.2 | |
| Coding | — | 46.9 | |
| Math | 85 | — | |
| Agentic | — | 7 | |
| Speed | — | 151 t/s | |
| TTFT | — | 2.21 s | |
| Input · $ / 1M tokens | — | $1.50 | |
| Output · $ / 1M tokens | — | $7.50 | |
| Context window | 128K | Best: 256K | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | — | $0.502 |
Intelligence
- ERNIE 5.0 Thinking Preview
- Best: 14.3
- Mistral Medium 3.5
- 14.2
Coding
- ERNIE 5.0 Thinking Preview
- —
- Mistral Medium 3.5
- 46.9
Math
- ERNIE 5.0 Thinking Preview
- 85
- Mistral Medium 3.5
- —
Agentic
- ERNIE 5.0 Thinking Preview
- —
- Mistral Medium 3.5
- 7
Speed
- ERNIE 5.0 Thinking Preview
- —
- Mistral Medium 3.5
- 151 t/s
TTFT
- ERNIE 5.0 Thinking Preview
- —
- Mistral Medium 3.5
- 2.21 s
Input · $ / 1M tokens
- ERNIE 5.0 Thinking Preview
- —
- Mistral Medium 3.5
- $1.50
Output · $ / 1M tokens
- ERNIE 5.0 Thinking Preview
- —
- Mistral Medium 3.5
- $7.50
Context window
- ERNIE 5.0 Thinking Preview
- 128K
- Mistral Medium 3.5
- Best: 256K
Reasoning
- ERNIE 5.0 Thinking Preview
- Yes
- Mistral Medium 3.5
- Yes
Open weights
- ERNIE 5.0 Thinking Preview
- No
- Mistral Medium 3.5
- Yes
Cost / task
- ERNIE 5.0 Thinking Preview
- —
- Mistral Medium 3.5
- $0.502
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 3.514.2 · $0.502
Not plotted for lack of data on these axes: ERNIE 5.0 Thinking Preview.