Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.4 (Non-reasoning)
OpenAI
- K2 Horizon 375B A23B
Institute of Foundation Models
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.4 (Non-reasoning) OpenAI | K2 Horizon 375B A23B Institute of Foundation Models | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 18.2 | 17.8 | |
| Coding | — | 61.5 | |
| Agentic | — | 40 | |
| Speed | 54.9 t/s | Best: 108 t/s | |
| TTFT | Best: 0.8 s | 2.74 s | |
| Input · $ / 1M tokens | $2.50 | — | |
| Output · $ / 1M tokens | $15 | — | |
| Context window | Best: 1.1M | 524K | |
| Reasoning | No | Yes | |
| Open weights | No | Yes | |
| Cost / task | — | $0 |
Intelligence
- GPT-5.4 (Non-reasoning)
- Best: 18.2
- K2 Horizon 375B A23B
- 17.8
Coding
- GPT-5.4 (Non-reasoning)
- —
- K2 Horizon 375B A23B
- 61.5
Agentic
- GPT-5.4 (Non-reasoning)
- —
- K2 Horizon 375B A23B
- 40
Speed
- GPT-5.4 (Non-reasoning)
- 54.9 t/s
- K2 Horizon 375B A23B
- Best: 108 t/s
TTFT
- GPT-5.4 (Non-reasoning)
- Best: 0.8 s
- K2 Horizon 375B A23B
- 2.74 s
Input · $ / 1M tokens
- GPT-5.4 (Non-reasoning)
- $2.50
- K2 Horizon 375B A23B
- —
Output · $ / 1M tokens
- GPT-5.4 (Non-reasoning)
- $15
- K2 Horizon 375B A23B
- —
Context window
- GPT-5.4 (Non-reasoning)
- Best: 1.1M
- K2 Horizon 375B A23B
- 524K
Reasoning
- GPT-5.4 (Non-reasoning)
- No
- K2 Horizon 375B A23B
- Yes
Open weights
- GPT-5.4 (Non-reasoning)
- No
- K2 Horizon 375B A23B
- Yes
Cost / task
- GPT-5.4 (Non-reasoning)
- —
- K2 Horizon 375B A23B
- $0
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.
- GPT-5.4 (Non-reasoning)18.2 · 54.9 t/s
- K2 Horizon 375B A23B17.8 · 108 t/s