Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3.8 27B (Low)
Alibaba
- 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 | Qwen3.8 27B (Low) Alibaba | K2 Horizon 3.7B Institute of Foundation Models | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 15.7 | 15.6 | |
| Coding | Best: 58.2 | 26.1 | |
| Agentic | Best: 38.9 | 16.5 | |
| Speed | 45.7 t/s | — | |
| TTFT | 3.97 s | — | |
| Input · $ / 1M tokens | $0.50 | — | |
| Output · $ / 1M tokens | $3 | — | |
| Context window | 256K | Best: 524K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $1.91 | — |
Intelligence
- Qwen3.8 27B (Low)
- Best: 15.7
- K2 Horizon 3.7B
- 15.6
Coding
- Qwen3.8 27B (Low)
- Best: 58.2
- K2 Horizon 3.7B
- 26.1
Agentic
- Qwen3.8 27B (Low)
- Best: 38.9
- K2 Horizon 3.7B
- 16.5
Speed
- Qwen3.8 27B (Low)
- 45.7 t/s
- K2 Horizon 3.7B
- —
TTFT
- Qwen3.8 27B (Low)
- 3.97 s
- K2 Horizon 3.7B
- —
Input · $ / 1M tokens
- Qwen3.8 27B (Low)
- $0.50
- K2 Horizon 3.7B
- —
Output · $ / 1M tokens
- Qwen3.8 27B (Low)
- $3
- K2 Horizon 3.7B
- —
Context window
- Qwen3.8 27B (Low)
- 256K
- K2 Horizon 3.7B
- Best: 524K
Reasoning
- Qwen3.8 27B (Low)
- Yes
- K2 Horizon 3.7B
- Yes
Open weights
- Qwen3.8 27B (Low)
- Yes
- K2 Horizon 3.7B
- Yes
Cost / task
- Qwen3.8 27B (Low)
- $1.91
- 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.
- Qwen3.8 27B (Low)15.7 · $1.91
Not plotted for lack of data on these axes: K2 Horizon 3.7B.