Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.6 Luna (Max)
OpenAI
- Claude Sonnet 5 (Max)
Anthropic
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.6 Luna (Max) OpenAI | Claude Sonnet 5 (Max) Anthropic | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 37.3 | Best: 38.2 | |
| Coding | 71.4 | Best: 71.5 | |
| Agentic | 42.1 | Best: 43.6 | |
| Speed | Best: 115 t/s | 74.7 t/s | |
| TTFT | Best: 121 s | 164 s | |
| Input · $ / 1M tokens | Best: $0.20 | $2×10 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $1.20 | $10×8.3 relative to the lowest price among the compared models | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $0.178 | $5.09×28.6 relative to the lowest price among the compared models |
Intelligence
- GPT-5.6 Luna (Max)
- 37.3
- Claude Sonnet 5 (Max)
- Best: 38.2
Coding
- GPT-5.6 Luna (Max)
- 71.4
- Claude Sonnet 5 (Max)
- Best: 71.5
Agentic
- GPT-5.6 Luna (Max)
- 42.1
- Claude Sonnet 5 (Max)
- Best: 43.6
Speed
- GPT-5.6 Luna (Max)
- Best: 115 t/s
- Claude Sonnet 5 (Max)
- 74.7 t/s
TTFT
- GPT-5.6 Luna (Max)
- Best: 121 s
- Claude Sonnet 5 (Max)
- 164 s
Input · $ / 1M tokens
- GPT-5.6 Luna (Max)
- Best: $0.20
- Claude Sonnet 5 (Max)
- $2×10 relative to the lowest price among the compared models
Output · $ / 1M tokens
- GPT-5.6 Luna (Max)
- Best: $1.20
- Claude Sonnet 5 (Max)
- $10×8.3 relative to the lowest price among the compared models
Context window
- GPT-5.6 Luna (Max)
- 1M
- Claude Sonnet 5 (Max)
- 1M
Reasoning
- GPT-5.6 Luna (Max)
- Yes
- Claude Sonnet 5 (Max)
- Yes
Open weights
- GPT-5.6 Luna (Max)
- No
- Claude Sonnet 5 (Max)
- No
Cost / task
- GPT-5.6 Luna (Max)
- Best: $0.178
- Claude Sonnet 5 (Max)
- $5.09×28.6 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 Luna (Max)37.3 · $0.178
- Claude Sonnet 5 (Max)38.2 · $5.09