Model Comparator
Compare up to four models using the same criteria.
2 models compared
- K2 Horizon 3.7B
Institute of Foundation Models
- Qwen3 Max
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | K2 Horizon 3.7B Institute of Foundation Models | Qwen3 Max Alibaba | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 15.6 | 15.6 | |
| Coding | 26.1 | — | |
| Math | — | 80.7 | |
| Agentic | 16.5 | — | |
| Speed | — | 61.2 t/s | |
| TTFT | — | 2.25 s | |
| Input · $ / 1M tokens | — | $1.20 | |
| Output · $ / 1M tokens | — | $6 | |
| Context window | Best: 524K | 262K | |
| Reasoning | Yes | No | |
| Open weights | Yes | No |
Intelligence
- K2 Horizon 3.7B
- 15.6
- Qwen3 Max
- 15.6
Coding
- K2 Horizon 3.7B
- 26.1
- Qwen3 Max
- —
Math
- K2 Horizon 3.7B
- —
- Qwen3 Max
- 80.7
Agentic
- K2 Horizon 3.7B
- 16.5
- Qwen3 Max
- —
Speed
- K2 Horizon 3.7B
- —
- Qwen3 Max
- 61.2 t/s
TTFT
- K2 Horizon 3.7B
- —
- Qwen3 Max
- 2.25 s
Input · $ / 1M tokens
- K2 Horizon 3.7B
- —
- Qwen3 Max
- $1.20
Output · $ / 1M tokens
- K2 Horizon 3.7B
- —
- Qwen3 Max
- $6
Context window
- K2 Horizon 3.7B
- Best: 524K
- Qwen3 Max
- 262K
Reasoning
- K2 Horizon 3.7B
- Yes
- Qwen3 Max
- No
Open weights
- K2 Horizon 3.7B
- Yes
- Qwen3 Max
- No
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 Max15.6 · $2.40
Not plotted for lack of data on these axes: K2 Horizon 3.7B.