Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.4 nano (Xhigh)
OpenAI
- Claude 4.5 Sonnet (Non-reasoning)
Anthropic
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.4 nano (Xhigh) OpenAI | Claude 4.5 Sonnet (Non-reasoning) Anthropic | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 20.7 | 20.7 | |
| Coding | Best: 56.1 | 52.1 | |
| Math | — | 37 | |
| Agentic | Best: 16 | 15.8 | |
| Speed | Best: 168 t/s | 39.3 t/s | |
| TTFT | 110 s | Best: 1.02 s | |
| Input · $ / 1M tokens | Best: $0.20 | $3×15 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $1.25 | $15×12 relative to the lowest price among the compared models | |
| Context window | 1M | 1M | |
| Reasoning | Yes | No | |
| Open weights | No | No | |
| Cost / task | $0.183 | — |
Intelligence
- GPT-5.4 nano (Xhigh)
- 20.7
- Claude 4.5 Sonnet (Non-reasoning)
- 20.7
Coding
- GPT-5.4 nano (Xhigh)
- Best: 56.1
- Claude 4.5 Sonnet (Non-reasoning)
- 52.1
Math
- GPT-5.4 nano (Xhigh)
- —
- Claude 4.5 Sonnet (Non-reasoning)
- 37
Agentic
- GPT-5.4 nano (Xhigh)
- Best: 16
- Claude 4.5 Sonnet (Non-reasoning)
- 15.8
Speed
- GPT-5.4 nano (Xhigh)
- Best: 168 t/s
- Claude 4.5 Sonnet (Non-reasoning)
- 39.3 t/s
TTFT
- GPT-5.4 nano (Xhigh)
- 110 s
- Claude 4.5 Sonnet (Non-reasoning)
- Best: 1.02 s
Input · $ / 1M tokens
- GPT-5.4 nano (Xhigh)
- Best: $0.20
- Claude 4.5 Sonnet (Non-reasoning)
- $3×15 relative to the lowest price among the compared models
Output · $ / 1M tokens
- GPT-5.4 nano (Xhigh)
- Best: $1.25
- Claude 4.5 Sonnet (Non-reasoning)
- $15×12 relative to the lowest price among the compared models
Context window
- GPT-5.4 nano (Xhigh)
- 1M
- Claude 4.5 Sonnet (Non-reasoning)
- 1M
Reasoning
- GPT-5.4 nano (Xhigh)
- Yes
- Claude 4.5 Sonnet (Non-reasoning)
- No
Open weights
- GPT-5.4 nano (Xhigh)
- No
- Claude 4.5 Sonnet (Non-reasoning)
- No
Cost / task
- GPT-5.4 nano (Xhigh)
- $0.183
- Claude 4.5 Sonnet (Non-reasoning)
- —
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 nano (Xhigh)20.7 · $0.463
- Claude 4.5 Sonnet (Non-reasoning)20.7 · $6