Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Sonnet 5 (Low)
Anthropic
- GPT-5.4 mini (Xhigh)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Sonnet 5 (Low) Anthropic | GPT-5.4 mini (Xhigh) OpenAI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 24.3 | 24.1 | |
| Coding | — | 56.1 | |
| Agentic | — | 17.9 | |
| Speed | 57.8 t/s | Best: 233 t/s | |
| TTFT | Best: 1.05 s | 114 s | |
| Input · $ / 1M tokens | $2×2.7 relative to the lowest price among the compared models | Best: $0.75 | |
| Output · $ / 1M tokens | $10×2.2 relative to the lowest price among the compared models | Best: $4.50 | |
| Context window | Best: 1M | 400K | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | $0.509×1.1 relative to the lowest price among the compared models | Best: $0.447 |
Intelligence
- Claude Sonnet 5 (Low)
- Best: 24.3
- GPT-5.4 mini (Xhigh)
- 24.1
Coding
- Claude Sonnet 5 (Low)
- —
- GPT-5.4 mini (Xhigh)
- 56.1
Agentic
- Claude Sonnet 5 (Low)
- —
- GPT-5.4 mini (Xhigh)
- 17.9
Speed
- Claude Sonnet 5 (Low)
- 57.8 t/s
- GPT-5.4 mini (Xhigh)
- Best: 233 t/s
TTFT
- Claude Sonnet 5 (Low)
- Best: 1.05 s
- GPT-5.4 mini (Xhigh)
- 114 s
Input · $ / 1M tokens
- Claude Sonnet 5 (Low)
- $2×2.7 relative to the lowest price among the compared models
- GPT-5.4 mini (Xhigh)
- Best: $0.75
Output · $ / 1M tokens
- Claude Sonnet 5 (Low)
- $10×2.2 relative to the lowest price among the compared models
- GPT-5.4 mini (Xhigh)
- Best: $4.50
Context window
- Claude Sonnet 5 (Low)
- Best: 1M
- GPT-5.4 mini (Xhigh)
- 400K
Reasoning
- Claude Sonnet 5 (Low)
- Yes
- GPT-5.4 mini (Xhigh)
- Yes
Open weights
- Claude Sonnet 5 (Low)
- No
- GPT-5.4 mini (Xhigh)
- No
Cost / task
- Claude Sonnet 5 (Low)
- $0.509×1.1 relative to the lowest price among the compared models
- GPT-5.4 mini (Xhigh)
- Best: $0.447
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 Sonnet 5 (Low)24.3 · $0.509
- GPT-5.4 mini (Xhigh)24.1 · $0.447