Model Comparator
Compare up to four models using the same criteria.
2 models compared
- K2 Horizon MoVA 36B A4B
Institute of Foundation Models
- Qwen3.7 Plus
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | K2 Horizon MoVA 36B A4B Institute of Foundation Models | Qwen3.7 Plus Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 25.3 | 25.2 | |
| Coding | — | 55.9 | |
| Agentic | Best: 33.5 | 17.5 | |
| Speed | — | 58 t/s | |
| TTFT | — | 2.44 s | |
| Input · $ / 1M tokens | — | $0.40 | |
| Output · $ / 1M tokens | — | $1.60 | |
| Context window | 524K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | No | |
| Cost / task | — | $0.217 |
Intelligence
- K2 Horizon MoVA 36B A4B
- Best: 25.3
- Qwen3.7 Plus
- 25.2
Coding
- K2 Horizon MoVA 36B A4B
- —
- Qwen3.7 Plus
- 55.9
Agentic
- K2 Horizon MoVA 36B A4B
- Best: 33.5
- Qwen3.7 Plus
- 17.5
Speed
- K2 Horizon MoVA 36B A4B
- —
- Qwen3.7 Plus
- 58 t/s
TTFT
- K2 Horizon MoVA 36B A4B
- —
- Qwen3.7 Plus
- 2.44 s
Input · $ / 1M tokens
- K2 Horizon MoVA 36B A4B
- —
- Qwen3.7 Plus
- $0.40
Output · $ / 1M tokens
- K2 Horizon MoVA 36B A4B
- —
- Qwen3.7 Plus
- $1.60
Context window
- K2 Horizon MoVA 36B A4B
- 524K
- Qwen3.7 Plus
- Best: 1M
Reasoning
- K2 Horizon MoVA 36B A4B
- Yes
- Qwen3.7 Plus
- Yes
Open weights
- K2 Horizon MoVA 36B A4B
- Yes
- Qwen3.7 Plus
- No
Cost / task
- K2 Horizon MoVA 36B A4B
- —
- Qwen3.7 Plus
- $0.217
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.
- Qwen3.7 Plus25.2 · $0.217
Not plotted for lack of data on these axes: K2 Horizon MoVA 36B A4B.