Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.4 nano (Xhigh)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.4 nano (Xhigh) OpenAI | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | Best: 20.8 | 20.7 | |
| Coding | 52.3 | Best: 56.1 | |
| Agentic | Best: 23.5 | 16 | |
| Speed | 90.1 t/s | Best: 166 t/s | |
| TTFT | Best: 0.81 s | 81 s | |
| Input · $ / 1M tokens | $2×10 relative to the lowest price among the compared models | Best: $0.20 | |
| Output · $ / 1M tokens | $12×9.6 relative to the lowest price among the compared models | Best: $1.25 | |
| Context window | Best: 1M | 400K | |
| Reasoning | No | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $0.14 | $0.183×1.3 relative to the lowest price among the compared models |
Intelligence
- GPT-5.6 Terra (Non-reasoning)
- Best: 20.8
- GPT-5.4 nano (Xhigh)
- 20.7
Coding
- GPT-5.6 Terra (Non-reasoning)
- 52.3
- GPT-5.4 nano (Xhigh)
- Best: 56.1
Agentic
- GPT-5.6 Terra (Non-reasoning)
- Best: 23.5
- GPT-5.4 nano (Xhigh)
- 16
Speed
- GPT-5.6 Terra (Non-reasoning)
- 90.1 t/s
- GPT-5.4 nano (Xhigh)
- Best: 166 t/s
TTFT
- GPT-5.6 Terra (Non-reasoning)
- Best: 0.81 s
- GPT-5.4 nano (Xhigh)
- 81 s
Input · $ / 1M tokens
- GPT-5.6 Terra (Non-reasoning)
- $2×10 relative to the lowest price among the compared models
- GPT-5.4 nano (Xhigh)
- Best: $0.20
Output · $ / 1M tokens
- GPT-5.6 Terra (Non-reasoning)
- $12×9.6 relative to the lowest price among the compared models
- GPT-5.4 nano (Xhigh)
- Best: $1.25
Context window
- GPT-5.6 Terra (Non-reasoning)
- Best: 1M
- GPT-5.4 nano (Xhigh)
- 400K
Reasoning
- GPT-5.6 Terra (Non-reasoning)
- No
- GPT-5.4 nano (Xhigh)
- Yes
Open weights
- GPT-5.6 Terra (Non-reasoning)
- No
- GPT-5.4 nano (Xhigh)
- No
Cost / task
- GPT-5.6 Terra (Non-reasoning)
- Best: $0.14
- GPT-5.4 nano (Xhigh)
- $0.183×1.3 relative to the lowest price among the compared models
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-5.6 Terra (Non-reasoning)20.8 · $0.14
- GPT-5.4 nano (Xhigh)20.7 · $0.183