Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Kimi K2 0905
Moonshot AI
- 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 | Kimi K2 0905 Moonshot AI | K2 Horizon 3.7B Institute of Foundation Models | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 15.3 | Best: 15.6 | |
| Coding | — | 26.1 | |
| Math | 57.3 | — | |
| Agentic | — | 16.5 | |
| Speed | 45.5 t/s | — | |
| TTFT | 1.69 s | — | |
| Input · $ / 1M tokens | $0.60 | — | |
| Output · $ / 1M tokens | $2.50 | — | |
| Context window | Best: 1M | 524K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes |
Intelligence
- Kimi K2 0905
- 15.3
- K2 Horizon 3.7B
- Best: 15.6
Coding
- Kimi K2 0905
- —
- K2 Horizon 3.7B
- 26.1
Math
- Kimi K2 0905
- 57.3
- K2 Horizon 3.7B
- —
Agentic
- Kimi K2 0905
- —
- K2 Horizon 3.7B
- 16.5
Speed
- Kimi K2 0905
- 45.5 t/s
- K2 Horizon 3.7B
- —
TTFT
- Kimi K2 0905
- 1.69 s
- K2 Horizon 3.7B
- —
Input · $ / 1M tokens
- Kimi K2 0905
- $0.60
- K2 Horizon 3.7B
- —
Output · $ / 1M tokens
- Kimi K2 0905
- $2.50
- K2 Horizon 3.7B
- —
Context window
- Kimi K2 0905
- Best: 1M
- K2 Horizon 3.7B
- 524K
Reasoning
- Kimi K2 0905
- No
- K2 Horizon 3.7B
- Yes
Open weights
- Kimi K2 0905
- Yes
- K2 Horizon 3.7B
- Yes
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.
- Kimi K2 090515.3 · $1.08
Not plotted for lack of data on these axes: K2 Horizon 3.7B.