Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Gemini 2.5 Pro
Google
- DeepSeek V3.2 (Non-reasoning)
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Gemini 2.5 Pro | DeepSeek V3.2 (Non-reasoning) DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 16.1 | 16 | |
| Coding | 33.3 | Best: 44.2 | |
| Math | Best: 87.7 | 59 | |
| Agentic | 1.6 | — | |
| Speed | 110 t/s | — | |
| TTFT | 23.8 s | — | |
| Input · $ / 1M tokens | $1.25×4.5 relative to the lowest price among the compared models | Best: $0.28 | |
| Output · $ / 1M tokens | $10×23.8 relative to the lowest price among the compared models | Best: $0.42 | |
| Context window | Best: 1M | 128K | |
| Reasoning | Yes | No | |
| Open weights | No | Yes | |
| Cost / task | $0.33 | — |
Intelligence
- Gemini 2.5 Pro
- Best: 16.1
- DeepSeek V3.2 (Non-reasoning)
- 16
Coding
- Gemini 2.5 Pro
- 33.3
- DeepSeek V3.2 (Non-reasoning)
- Best: 44.2
Math
- Gemini 2.5 Pro
- Best: 87.7
- DeepSeek V3.2 (Non-reasoning)
- 59
Agentic
- Gemini 2.5 Pro
- 1.6
- DeepSeek V3.2 (Non-reasoning)
- —
Speed
- Gemini 2.5 Pro
- 110 t/s
- DeepSeek V3.2 (Non-reasoning)
- —
TTFT
- Gemini 2.5 Pro
- 23.8 s
- DeepSeek V3.2 (Non-reasoning)
- —
Input · $ / 1M tokens
- Gemini 2.5 Pro
- $1.25×4.5 relative to the lowest price among the compared models
- DeepSeek V3.2 (Non-reasoning)
- Best: $0.28
Output · $ / 1M tokens
- Gemini 2.5 Pro
- $10×23.8 relative to the lowest price among the compared models
- DeepSeek V3.2 (Non-reasoning)
- Best: $0.42
Context window
- Gemini 2.5 Pro
- Best: 1M
- DeepSeek V3.2 (Non-reasoning)
- 128K
Reasoning
- Gemini 2.5 Pro
- Yes
- DeepSeek V3.2 (Non-reasoning)
- No
Open weights
- Gemini 2.5 Pro
- No
- DeepSeek V3.2 (Non-reasoning)
- Yes
Cost / task
- Gemini 2.5 Pro
- $0.33
- DeepSeek V3.2 (Non-reasoning)
- —
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.
- Gemini 2.5 Pro16.1 · $3.44
- DeepSeek V3.2 (Non-reasoning)16 · $0.315