Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.6 Luna (Max)
OpenAI
- Claude Haiku 5.5 (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 Haiku 5.5 (Max) Anthropic | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 37.3 | 36.5 | |
| Coding | 71.4 | — | |
| Agentic | 42.1 | — | |
| Speed | 104 t/s | Best: 236 t/s | |
| TTFT | Best: 139 s | 283 s | |
| Input · $ / 1M tokens | $0.20×2 relative to the lowest price among the compared models | Best: $0.10 | |
| Output · $ / 1M tokens | $1.20×2.4 relative to the lowest price among the compared models | Best: $0.50 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $0.178 | $0.411×2.3 relative to the lowest price among the compared models |
Intelligence
- GPT-5.6 Luna (Max)
- Best: 37.3
- Claude Haiku 5.5 (Max)
- 36.5
Coding
- GPT-5.6 Luna (Max)
- 71.4
- Claude Haiku 5.5 (Max)
- —
Agentic
- GPT-5.6 Luna (Max)
- 42.1
- Claude Haiku 5.5 (Max)
- —
Speed
- GPT-5.6 Luna (Max)
- 104 t/s
- Claude Haiku 5.5 (Max)
- Best: 236 t/s
TTFT
- GPT-5.6 Luna (Max)
- Best: 139 s
- Claude Haiku 5.5 (Max)
- 283 s
Input · $ / 1M tokens
- GPT-5.6 Luna (Max)
- $0.20×2 relative to the lowest price among the compared models
- Claude Haiku 5.5 (Max)
- Best: $0.10
Output · $ / 1M tokens
- GPT-5.6 Luna (Max)
- $1.20×2.4 relative to the lowest price among the compared models
- Claude Haiku 5.5 (Max)
- Best: $0.50
Context window
- GPT-5.6 Luna (Max)
- 1M
- Claude Haiku 5.5 (Max)
- 1M
Reasoning
- GPT-5.6 Luna (Max)
- Yes
- Claude Haiku 5.5 (Max)
- Yes
Open weights
- GPT-5.6 Luna (Max)
- No
- Claude Haiku 5.5 (Max)
- No
Cost / task
- GPT-5.6 Luna (Max)
- Best: $0.178
- Claude Haiku 5.5 (Max)
- $0.411×2.3 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 Haiku 5.5 (Max)36.5 · $0.411