Model Comparator
Compare up to four models using the same criteria.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | 5.5 | 5.5 | |
| Coding | 9.7 | — | |
| Math | — | 22 | |
| Agentic | 0.6 | — | |
| Input · $ / 1M tokens | $0.15 | — | |
| Output · $ / 1M tokens | $0.15 | — | |
| Context window | Best: 262K | 128K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes |
Intelligence
- Ministral 3 8B 2512
- 5.5
- DeepSeek R1 Distill Qwen 1.5B
- 5.5
Coding
- Ministral 3 8B 2512
- 9.7
- DeepSeek R1 Distill Qwen 1.5B
- —
Math
- Ministral 3 8B 2512
- —
- DeepSeek R1 Distill Qwen 1.5B
- 22
Agentic
- Ministral 3 8B 2512
- 0.6
- DeepSeek R1 Distill Qwen 1.5B
- —
Input · $ / 1M tokens
- Ministral 3 8B 2512
- $0.15
- DeepSeek R1 Distill Qwen 1.5B
- —
Output · $ / 1M tokens
- Ministral 3 8B 2512
- $0.15
- DeepSeek R1 Distill Qwen 1.5B
- —
Context window
- Ministral 3 8B 2512
- Best: 262K
- DeepSeek R1 Distill Qwen 1.5B
- 128K
Reasoning
- Ministral 3 8B 2512
- No
- DeepSeek R1 Distill Qwen 1.5B
- Yes
Open weights
- Ministral 3 8B 2512
- Yes
- DeepSeek R1 Distill Qwen 1.5B
- 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.
- Ministral 3 8B 25125.5 · $0.15
Not plotted for lack of data on these axes: DeepSeek R1 Distill Qwen 1.5B.