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 | 3.8 | Best: 4.4 | |
| Coding | 5.8 | Best: 43.4 | |
| Math | 18.3 | — | |
| Agentic | 0.1 | Best: 4.2 | |
| Speed | Best: 52.6 t/s | 23.6 t/s | |
| TTFT | 2.94 s | Best: 0.97 s | |
| Context window | 128K | Best: 256K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0 | $0 |
Intelligence
- Gemma 3 12B Instruct
- 3.8
- Gemma 4 31B (Reasoning)
- Best: 4.4
Coding
- Gemma 3 12B Instruct
- 5.8
- Gemma 4 31B (Reasoning)
- Best: 43.4
Math
- Gemma 3 12B Instruct
- 18.3
- Gemma 4 31B (Reasoning)
- —
Agentic
- Gemma 3 12B Instruct
- 0.1
- Gemma 4 31B (Reasoning)
- Best: 4.2
Speed
- Gemma 3 12B Instruct
- Best: 52.6 t/s
- Gemma 4 31B (Reasoning)
- 23.6 t/s
TTFT
- Gemma 3 12B Instruct
- 2.94 s
- Gemma 4 31B (Reasoning)
- Best: 0.97 s
Context window
- Gemma 3 12B Instruct
- 128K
- Gemma 4 31B (Reasoning)
- Best: 256K
Reasoning
- Gemma 3 12B Instruct
- No
- Gemma 4 31B (Reasoning)
- Yes
Open weights
- Gemma 3 12B Instruct
- Yes
- Gemma 4 31B (Reasoning)
- Yes
Cost / task
- Gemma 3 12B Instruct
- $0
- Gemma 4 31B (Reasoning)
- $0
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 3 12B Instruct3.8 · $0
- Gemma 4 31B (Reasoning)4.4 · $0