Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude Opus 5 (High)
Anthropic
- GPT-5.6 Sol (Max)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude Opus 5 (High) Anthropic | GPT-5.6 Sol (Max) OpenAI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 48.1 | 47 | |
| Coding | 76.5 | Best: 77.4 | |
| Agentic | Best: 52.3 | 50.2 | |
| Speed | 52.5 t/s | Best: 80.9 t/s | |
| TTFT | Best: 10.4 s | 74 s | |
| Input · $ / 1M tokens | $5×1.3 relative to the lowest price among the compared models | Best: $4 | |
| Output · $ / 1M tokens | $25×1.3 relative to the lowest price among the compared models | Best: $20 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | $3.61×1.8 relative to the lowest price among the compared models | Best: $1.99 |
Intelligence
- Claude Opus 5 (High)
- Best: 48.1
- GPT-5.6 Sol (Max)
- 47
Coding
- Claude Opus 5 (High)
- 76.5
- GPT-5.6 Sol (Max)
- Best: 77.4
Agentic
- Claude Opus 5 (High)
- Best: 52.3
- GPT-5.6 Sol (Max)
- 50.2
Speed
- Claude Opus 5 (High)
- 52.5 t/s
- GPT-5.6 Sol (Max)
- Best: 80.9 t/s
TTFT
- Claude Opus 5 (High)
- Best: 10.4 s
- GPT-5.6 Sol (Max)
- 74 s
Input · $ / 1M tokens
- Claude Opus 5 (High)
- $5×1.3 relative to the lowest price among the compared models
- GPT-5.6 Sol (Max)
- Best: $4
Output · $ / 1M tokens
- Claude Opus 5 (High)
- $25×1.3 relative to the lowest price among the compared models
- GPT-5.6 Sol (Max)
- Best: $20
Context window
- Claude Opus 5 (High)
- 1M
- GPT-5.6 Sol (Max)
- 1M
Reasoning
- Claude Opus 5 (High)
- Yes
- GPT-5.6 Sol (Max)
- Yes
Open weights
- Claude Opus 5 (High)
- No
- GPT-5.6 Sol (Max)
- No
Cost / task
- Claude Opus 5 (High)
- $3.61×1.8 relative to the lowest price among the compared models
- GPT-5.6 Sol (Max)
- Best: $1.99
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 Opus 5 (High)48.1 · $3.61
- GPT-5.6 Sol (Max)47 · $1.99