Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5 Mini (batch)
OpenAI
- K2 Horizon 7B
Institute of Foundation Models
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5 Mini (batch) OpenAI | K2 Horizon 7B Institute of Foundation Models | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 20.6 | 20.6 | |
| Coding | 15.6 | Best: 38.6 | |
| Agentic | 6.8 | Best: 26.1 | |
| Context window | 400K | Best: 524K | |
| Reasoning | Yes | Yes | |
| Open weights | — | Yes |
Intelligence
- GPT-5 Mini (batch)
- 20.6
- K2 Horizon 7B
- 20.6
Coding
- GPT-5 Mini (batch)
- 15.6
- K2 Horizon 7B
- Best: 38.6
Agentic
- GPT-5 Mini (batch)
- 6.8
- K2 Horizon 7B
- Best: 26.1
Context window
- GPT-5 Mini (batch)
- 400K
- K2 Horizon 7B
- Best: 524K
Reasoning
- GPT-5 Mini (batch)
- Yes
- K2 Horizon 7B
- Yes
Open weights
- GPT-5 Mini (batch)
- —
- K2 Horizon 7B
- Yes
Each reasoning level remains a separate configuration.