Model Comparator
Compare up to four models using the same criteria.
2 models compared
- DeepSeek V3.1 (Non-reasoning)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | DeepSeek V3.1 (Non-reasoning) DeepSeek | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | Best: 13.9 | 13.7 | |
| Coding | 43.5 | — | |
| Math | Best: 53.7 | 49.7 | |
| Agentic | 6.8 | — | |
| Speed | 40.8 t/s | Best: 98 t/s | |
| TTFT | Best: 1.15 s | 1.39 s | |
| Input · $ / 1M tokens | Best: $0.27 | $0.56×2.1 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $1 | $1.68×1.7 relative to the lowest price among the compared models | |
| Context window | 128K | 128K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- DeepSeek V3.1 Terminus (Non-reasoning)
- Best: 13.9
- DeepSeek V3.1 (Non-reasoning)
- 13.7
Coding
- DeepSeek V3.1 Terminus (Non-reasoning)
- 43.5
- DeepSeek V3.1 (Non-reasoning)
- —
Math
- DeepSeek V3.1 Terminus (Non-reasoning)
- Best: 53.7
- DeepSeek V3.1 (Non-reasoning)
- 49.7
Agentic
- DeepSeek V3.1 Terminus (Non-reasoning)
- 6.8
- DeepSeek V3.1 (Non-reasoning)
- —
Speed
- DeepSeek V3.1 Terminus (Non-reasoning)
- 40.8 t/s
- DeepSeek V3.1 (Non-reasoning)
- Best: 98 t/s
TTFT
- DeepSeek V3.1 Terminus (Non-reasoning)
- Best: 1.15 s
- DeepSeek V3.1 (Non-reasoning)
- 1.39 s
Input · $ / 1M tokens
- DeepSeek V3.1 Terminus (Non-reasoning)
- Best: $0.27
- DeepSeek V3.1 (Non-reasoning)
- $0.56×2.1 relative to the lowest price among the compared models
Output · $ / 1M tokens
- DeepSeek V3.1 Terminus (Non-reasoning)
- Best: $1
- DeepSeek V3.1 (Non-reasoning)
- $1.68×1.7 relative to the lowest price among the compared models
Context window
- DeepSeek V3.1 Terminus (Non-reasoning)
- 128K
- DeepSeek V3.1 (Non-reasoning)
- 128K
Reasoning
- DeepSeek V3.1 Terminus (Non-reasoning)
- No
- DeepSeek V3.1 (Non-reasoning)
- No
Open weights
- DeepSeek V3.1 Terminus (Non-reasoning)
- Yes
- DeepSeek V3.1 (Non-reasoning)
- 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 Terminus (Non-reasoning)13.9 · $0.453
- DeepSeek V3.1 (Non-reasoning)13.7 · $0.84