Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.5 (Xhigh)
OpenAI
- Claude Sonnet 5 (Max)
Anthropic
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.5 (Xhigh) OpenAI | Claude Sonnet 5 (Max) Anthropic | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 38.4 | 38.2 | |
| Coding | Best: 74.9 | 71.5 | |
| Agentic | 36.4 | Best: 43.6 | |
| Speed | Best: 81.9 t/s | 74.7 t/s | |
| TTFT | Best: 58.6 s | 164 s | |
| Input · $ / 1M tokens | $5×2.5 relative to the lowest price among the compared models | Best: $2 | |
| Output · $ / 1M tokens | $30×3 relative to the lowest price among the compared models | Best: $10 | |
| Context window | 922K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $2.63 | $5.09×1.9 relative to the lowest price among the compared models |
Intelligence
- GPT-5.5 (Xhigh)
- Best: 38.4
- Claude Sonnet 5 (Max)
- 38.2
Coding
- GPT-5.5 (Xhigh)
- Best: 74.9
- Claude Sonnet 5 (Max)
- 71.5
Agentic
- GPT-5.5 (Xhigh)
- 36.4
- Claude Sonnet 5 (Max)
- Best: 43.6
Speed
- GPT-5.5 (Xhigh)
- Best: 81.9 t/s
- Claude Sonnet 5 (Max)
- 74.7 t/s
TTFT
- GPT-5.5 (Xhigh)
- Best: 58.6 s
- Claude Sonnet 5 (Max)
- 164 s
Input · $ / 1M tokens
- GPT-5.5 (Xhigh)
- $5×2.5 relative to the lowest price among the compared models
- Claude Sonnet 5 (Max)
- Best: $2
Output · $ / 1M tokens
- GPT-5.5 (Xhigh)
- $30×3 relative to the lowest price among the compared models
- Claude Sonnet 5 (Max)
- Best: $10
Context window
- GPT-5.5 (Xhigh)
- 922K
- Claude Sonnet 5 (Max)
- Best: 1M
Reasoning
- GPT-5.5 (Xhigh)
- Yes
- Claude Sonnet 5 (Max)
- Yes
Open weights
- GPT-5.5 (Xhigh)
- No
- Claude Sonnet 5 (Max)
- No
Cost / task
- GPT-5.5 (Xhigh)
- Best: $2.63
- Claude Sonnet 5 (Max)
- $5.09×1.9 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-5.5 (Xhigh)38.4 · $2.63
- Claude Sonnet 5 (Max)38.2 · $5.09