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 | Best: 3.8 | |
| Coding | 3.4 | Best: 5.8 | |
| Math | — | 18.3 | |
| Agentic | Best: 0.8 | 0.1 | |
| Speed | — | 52.6 t/s | |
| TTFT | — | 2.94 s | |
| Context window | Best: 131K | 128K | |
| Reasoning | Yes | No | |
| Open weights | Yes | Yes | |
| Cost / task | — | $0 |
Intelligence
- K2 Horizon 0.9B
- 3
- Gemma 3 12B Instruct
- Best: 3.8
Coding
- K2 Horizon 0.9B
- 3.4
- Gemma 3 12B Instruct
- Best: 5.8
Math
- K2 Horizon 0.9B
- —
- Gemma 3 12B Instruct
- 18.3
Agentic
- K2 Horizon 0.9B
- Best: 0.8
- Gemma 3 12B Instruct
- 0.1
Speed
- K2 Horizon 0.9B
- —
- Gemma 3 12B Instruct
- 52.6 t/s
TTFT
- K2 Horizon 0.9B
- —
- Gemma 3 12B Instruct
- 2.94 s
Context window
- K2 Horizon 0.9B
- Best: 131K
- Gemma 3 12B Instruct
- 128K
Reasoning
- K2 Horizon 0.9B
- Yes
- Gemma 3 12B Instruct
- No
Open weights
- K2 Horizon 0.9B
- Yes
- Gemma 3 12B Instruct
- Yes
Cost / task
- K2 Horizon 0.9B
- —
- Gemma 3 12B Instruct
- $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
Not plotted for lack of data on these axes: K2 Horizon 0.9B.