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