Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V3.1 (Non-reasoning)
DeepSeek
- Apriel-v1.6-15B-Thinker
ServiceNow
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V3.1 (Non-reasoning) DeepSeek | Apriel-v1.6-15B-Thinker ServiceNow | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 13.7 | 13.4 | |
| Math | 49.7 | Best: 88 | |
| Speed | 96.6 t/s | — | |
| TTFT | 1.41 s | — | |
| Input · $ / 1M tokens | $0.56 | — | |
| Output · $ / 1M tokens | $1.68 | — | |
| Context window | 128K | 128K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes |
Intelligence
- DeepSeek V3.1 (Non-reasoning)
- Best: 13.7
- Apriel-v1.6-15B-Thinker
- 13.4
Math
- DeepSeek V3.1 (Non-reasoning)
- 49.7
- Apriel-v1.6-15B-Thinker
- Best: 88
Speed
- DeepSeek V3.1 (Non-reasoning)
- 96.6 t/s
- Apriel-v1.6-15B-Thinker
- —
TTFT
- DeepSeek V3.1 (Non-reasoning)
- 1.41 s
- Apriel-v1.6-15B-Thinker
- —
Input · $ / 1M tokens
- DeepSeek V3.1 (Non-reasoning)
- $0.56
- Apriel-v1.6-15B-Thinker
- —
Output · $ / 1M tokens
- DeepSeek V3.1 (Non-reasoning)
- $1.68
- Apriel-v1.6-15B-Thinker
- —
Context window
- DeepSeek V3.1 (Non-reasoning)
- 128K
- Apriel-v1.6-15B-Thinker
- 128K
Reasoning
- DeepSeek V3.1 (Non-reasoning)
- No
- Apriel-v1.6-15B-Thinker
- Yes
Open weights
- DeepSeek V3.1 (Non-reasoning)
- Yes
- Apriel-v1.6-15B-Thinker
- 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.
- DeepSeek V3.1 (Non-reasoning)13.7 · $0.84
Not plotted for lack of data on these axes: Apriel-v1.6-15B-Thinker.