Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Gemini 2.5 Pro
Google
- K2 Horizon 3.7B
Institute of Foundation Models
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Gemini 2.5 Pro | K2 Horizon 3.7B Institute of Foundation Models | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 16.1 | 15.6 | |
| Coding | Best: 33.3 | 26.1 | |
| Math | 87.7 | — | |
| Agentic | 1.6 | Best: 16.5 | |
| Speed | 104 t/s | — | |
| TTFT | 26.3 s | — | |
| Input · $ / 1M tokens | $1.25 | — | |
| Output · $ / 1M tokens | $10 | — | |
| Context window | Best: 1M | 524K | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | $0.314 | — |
Intelligence
- Gemini 2.5 Pro
- Best: 16.1
- K2 Horizon 3.7B
- 15.6
Coding
- Gemini 2.5 Pro
- Best: 33.3
- K2 Horizon 3.7B
- 26.1
Math
- Gemini 2.5 Pro
- 87.7
- K2 Horizon 3.7B
- —
Agentic
- Gemini 2.5 Pro
- 1.6
- K2 Horizon 3.7B
- Best: 16.5
Speed
- Gemini 2.5 Pro
- 104 t/s
- K2 Horizon 3.7B
- —
TTFT
- Gemini 2.5 Pro
- 26.3 s
- K2 Horizon 3.7B
- —
Input · $ / 1M tokens
- Gemini 2.5 Pro
- $1.25
- K2 Horizon 3.7B
- —
Output · $ / 1M tokens
- Gemini 2.5 Pro
- $10
- K2 Horizon 3.7B
- —
Context window
- Gemini 2.5 Pro
- Best: 1M
- K2 Horizon 3.7B
- 524K
Reasoning
- Gemini 2.5 Pro
- Yes
- K2 Horizon 3.7B
- Yes
Open weights
- Gemini 2.5 Pro
- No
- K2 Horizon 3.7B
- Yes
Cost / task
- Gemini 2.5 Pro
- $0.314
- K2 Horizon 3.7B
- —
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 · $0.314
Not plotted for lack of data on these axes: K2 Horizon 3.7B.