Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5 mini (High)
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 (High) OpenAI | K2 Horizon 7B Institute of Foundation Models | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 20.6 | 20.6 | |
| Coding | 15.6 | Best: 38.6 | |
| Math | 90.7 | — | |
| Agentic | 6.8 | Best: 26.1 | |
| Speed | 89.4 t/s | — | |
| TTFT | 66 s | — | |
| Input · $ / 1M tokens | $0.25 | — | |
| Output · $ / 1M tokens | $2 | — | |
| Context window | Best: 1M | 524K | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | $0.0535 | — |
Intelligence
- GPT-5 mini (High)
- 20.6
- K2 Horizon 7B
- 20.6
Coding
- GPT-5 mini (High)
- 15.6
- K2 Horizon 7B
- Best: 38.6
Math
- GPT-5 mini (High)
- 90.7
- K2 Horizon 7B
- —
Agentic
- GPT-5 mini (High)
- 6.8
- K2 Horizon 7B
- Best: 26.1
Speed
- GPT-5 mini (High)
- 89.4 t/s
- K2 Horizon 7B
- —
TTFT
- GPT-5 mini (High)
- 66 s
- K2 Horizon 7B
- —
Input · $ / 1M tokens
- GPT-5 mini (High)
- $0.25
- K2 Horizon 7B
- —
Output · $ / 1M tokens
- GPT-5 mini (High)
- $2
- K2 Horizon 7B
- —
Context window
- GPT-5 mini (High)
- Best: 1M
- K2 Horizon 7B
- 524K
Reasoning
- GPT-5 mini (High)
- Yes
- K2 Horizon 7B
- Yes
Open weights
- GPT-5 mini (High)
- No
- K2 Horizon 7B
- Yes
Cost / task
- GPT-5 mini (High)
- $0.0535
- K2 Horizon 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.
- GPT-5 mini (High)20.6 · $0.0535
Not plotted for lack of data on these axes: K2 Horizon 7B.