Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Devstral 2
Mistral
- Claude 3 Opus
Anthropic
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Devstral 2 Mistral | Claude 3 Opus Anthropic | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 8.6 | Best: 8.7 | |
| Coding | Best: 31.3 | 19.5 | |
| Math | 36.7 | — | |
| Agentic | 2.3 | — | |
| Speed | 139 t/s | — | |
| TTFT | 2.34 s | — | |
| Input · $ / 1M tokens | — | $15 | |
| Output · $ / 1M tokens | — | $75 | |
| Context window | Best: 256K | 200K | |
| Reasoning | No | No | |
| Open weights | Yes | No |
Intelligence
- Devstral 2
- 8.6
- Claude 3 Opus
- Best: 8.7
Coding
- Devstral 2
- Best: 31.3
- Claude 3 Opus
- 19.5
Math
- Devstral 2
- 36.7
- Claude 3 Opus
- —
Agentic
- Devstral 2
- 2.3
- Claude 3 Opus
- —
Speed
- Devstral 2
- 139 t/s
- Claude 3 Opus
- —
TTFT
- Devstral 2
- 2.34 s
- Claude 3 Opus
- —
Input · $ / 1M tokens
- Devstral 2
- —
- Claude 3 Opus
- $15
Output · $ / 1M tokens
- Devstral 2
- —
- Claude 3 Opus
- $75
Context window
- Devstral 2
- Best: 256K
- Claude 3 Opus
- 200K
Reasoning
- Devstral 2
- No
- Claude 3 Opus
- No
Open weights
- Devstral 2
- Yes
- Claude 3 Opus
- No
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.
- Devstral 28.6 · $0
Not plotted for lack of data on these axes: Claude 3 Opus.