Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Devstral 2
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Devstral 2 Mistral | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 8.5 | Best: 8.6 | |
| Coding | — | 31.3 | |
| Math | Best: 53.3 | 36.7 | |
| Agentic | — | 2.3 | |
| Speed | Best: 355 t/s | 139 t/s | |
| TTFT | 17.5 s | Best: 2.34 s | |
| Input · $ / 1M tokens | $0.10 | — | |
| Output · $ / 1M tokens | $0.40 | — | |
| Context window | Best: 1M | 256K | |
| Reasoning | Yes | No | |
| Open weights | No | Yes |
Intelligence
- Gemini 2.5 Flash-Lite (Reasoning)
- 8.5
- Devstral 2
- Best: 8.6
Coding
- Gemini 2.5 Flash-Lite (Reasoning)
- —
- Devstral 2
- 31.3
Math
- Gemini 2.5 Flash-Lite (Reasoning)
- Best: 53.3
- Devstral 2
- 36.7
Agentic
- Gemini 2.5 Flash-Lite (Reasoning)
- —
- Devstral 2
- 2.3
Speed
- Gemini 2.5 Flash-Lite (Reasoning)
- Best: 355 t/s
- Devstral 2
- 139 t/s
TTFT
- Gemini 2.5 Flash-Lite (Reasoning)
- 17.5 s
- Devstral 2
- Best: 2.34 s
Input · $ / 1M tokens
- Gemini 2.5 Flash-Lite (Reasoning)
- $0.10
- Devstral 2
- —
Output · $ / 1M tokens
- Gemini 2.5 Flash-Lite (Reasoning)
- $0.40
- Devstral 2
- —
Context window
- Gemini 2.5 Flash-Lite (Reasoning)
- Best: 1M
- Devstral 2
- 256K
Reasoning
- Gemini 2.5 Flash-Lite (Reasoning)
- Yes
- Devstral 2
- No
Open weights
- Gemini 2.5 Flash-Lite (Reasoning)
- No
- Devstral 2
- 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.
- Gemini 2.5 Flash-Lite (Reasoning)8.5 · 355 t/s
- Devstral 28.6 · 139 t/s