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 | 14.8 | Best: 15 | |
| Coding | 43.5 | Best: 46.7 | |
| Math | 89.7 | — | |
| Agentic | 6.8 | — | |
| Input · $ / 1M tokens | $1.64 | — | |
| Output · $ / 1M tokens | $2.75 | — | |
| Context window | 128K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No |
Intelligence
- DeepSeek V3.1 Terminus (Reasoning)
- 14.8
- Gemini 2.5 Pro Preview (Mar' 25)
- Best: 15
Coding
- DeepSeek V3.1 Terminus (Reasoning)
- 43.5
- Gemini 2.5 Pro Preview (Mar' 25)
- Best: 46.7
Math
- DeepSeek V3.1 Terminus (Reasoning)
- 89.7
- Gemini 2.5 Pro Preview (Mar' 25)
- —
Agentic
- DeepSeek V3.1 Terminus (Reasoning)
- 6.8
- Gemini 2.5 Pro Preview (Mar' 25)
- —
Input · $ / 1M tokens
- DeepSeek V3.1 Terminus (Reasoning)
- $1.64
- Gemini 2.5 Pro Preview (Mar' 25)
- —
Output · $ / 1M tokens
- DeepSeek V3.1 Terminus (Reasoning)
- $2.75
- Gemini 2.5 Pro Preview (Mar' 25)
- —
Context window
- DeepSeek V3.1 Terminus (Reasoning)
- 128K
- Gemini 2.5 Pro Preview (Mar' 25)
- Best: 1M
Reasoning
- DeepSeek V3.1 Terminus (Reasoning)
- Yes
- Gemini 2.5 Pro Preview (Mar' 25)
- Yes
Open weights
- DeepSeek V3.1 Terminus (Reasoning)
- Yes
- Gemini 2.5 Pro Preview (Mar' 25)
- 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.
- DeepSeek V3.1 Terminus (Reasoning)14.8 · $1.91
Not plotted for lack of data on these axes: Gemini 2.5 Pro Preview (Mar' 25).