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 | 13.9 | 13.9 | |
| Coding | 33.2 | Best: 43.5 | |
| Math | — | 53.7 | |
| Agentic | — | 6.8 | |
| Speed | Best: 48 t/s | 40.8 t/s | |
| TTFT | 1.97 s | Best: 1.15 s | |
| Input · $ / 1M tokens | Best: $0.165 | $0.27×1.6 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.40 | $1×2.5 relative to the lowest price among the compared models | |
| Context window | Best: 256K | 128K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Gemma 4 31B (Non-reasoning)
- 13.9
- DeepSeek V3.1 Terminus (Non-reasoning)
- 13.9
Coding
- Gemma 4 31B (Non-reasoning)
- 33.2
- DeepSeek V3.1 Terminus (Non-reasoning)
- Best: 43.5
Math
- Gemma 4 31B (Non-reasoning)
- —
- DeepSeek V3.1 Terminus (Non-reasoning)
- 53.7
Agentic
- Gemma 4 31B (Non-reasoning)
- —
- DeepSeek V3.1 Terminus (Non-reasoning)
- 6.8
Speed
- Gemma 4 31B (Non-reasoning)
- Best: 48 t/s
- DeepSeek V3.1 Terminus (Non-reasoning)
- 40.8 t/s
TTFT
- Gemma 4 31B (Non-reasoning)
- 1.97 s
- DeepSeek V3.1 Terminus (Non-reasoning)
- Best: 1.15 s
Input · $ / 1M tokens
- Gemma 4 31B (Non-reasoning)
- Best: $0.165
- DeepSeek V3.1 Terminus (Non-reasoning)
- $0.27×1.6 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Gemma 4 31B (Non-reasoning)
- Best: $0.40
- DeepSeek V3.1 Terminus (Non-reasoning)
- $1×2.5 relative to the lowest price among the compared models
Context window
- Gemma 4 31B (Non-reasoning)
- Best: 256K
- DeepSeek V3.1 Terminus (Non-reasoning)
- 128K
Reasoning
- Gemma 4 31B (Non-reasoning)
- No
- DeepSeek V3.1 Terminus (Non-reasoning)
- No
Open weights
- Gemma 4 31B (Non-reasoning)
- Yes
- DeepSeek V3.1 Terminus (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.
- Gemma 4 31B (Non-reasoning)13.9 · $0.224
- DeepSeek V3.1 Terminus (Non-reasoning)13.9 · $0.453