Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude 4.5 Haiku (Non-reasoning)
Anthropic
- 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 | Claude 4.5 Haiku (Non-reasoning) Anthropic | K2 Horizon 3.7B Institute of Foundation Models | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 15.4 | Best: 15.6 | |
| Coding | Best: 43.9 | 26.1 | |
| Math | 39 | — | |
| Agentic | 8 | Best: 16.5 | |
| Speed | 87.8 t/s | — | |
| TTFT | 0.5 s | — | |
| Input · $ / 1M tokens | $1 | — | |
| Output · $ / 1M tokens | $5 | — | |
| Context window | 200K | Best: 524K | |
| Reasoning | No | Yes | |
| Open weights | No | Yes |
Intelligence
- Claude 4.5 Haiku (Non-reasoning)
- 15.4
- K2 Horizon 3.7B
- Best: 15.6
Coding
- Claude 4.5 Haiku (Non-reasoning)
- Best: 43.9
- K2 Horizon 3.7B
- 26.1
Math
- Claude 4.5 Haiku (Non-reasoning)
- 39
- K2 Horizon 3.7B
- —
Agentic
- Claude 4.5 Haiku (Non-reasoning)
- 8
- K2 Horizon 3.7B
- Best: 16.5
Speed
- Claude 4.5 Haiku (Non-reasoning)
- 87.8 t/s
- K2 Horizon 3.7B
- —
TTFT
- Claude 4.5 Haiku (Non-reasoning)
- 0.5 s
- K2 Horizon 3.7B
- —
Input · $ / 1M tokens
- Claude 4.5 Haiku (Non-reasoning)
- $1
- K2 Horizon 3.7B
- —
Output · $ / 1M tokens
- Claude 4.5 Haiku (Non-reasoning)
- $5
- K2 Horizon 3.7B
- —
Context window
- Claude 4.5 Haiku (Non-reasoning)
- 200K
- K2 Horizon 3.7B
- Best: 524K
Reasoning
- Claude 4.5 Haiku (Non-reasoning)
- No
- K2 Horizon 3.7B
- Yes
Open weights
- Claude 4.5 Haiku (Non-reasoning)
- No
- 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.
- Claude 4.5 Haiku (Non-reasoning)15.4 · $2
Not plotted for lack of data on these axes: K2 Horizon 3.7B.