Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude 4.5 Haiku (Non-reasoning)
Anthropic
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude 4.5 Haiku (Non-reasoning) Anthropic | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | Best: 15.5 | 15.4 | |
| Coding | 39.3 | Best: 43.9 | |
| Math | — | 39 | |
| Agentic | Best: 13.4 | 8 | |
| Speed | Best: 118 t/s | 87.8 t/s | |
| TTFT | 0.76 s | Best: 0.5 s | |
| Input · $ / 1M tokens | Best: $0.20 | $1×5 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $1.20 | $5×4.2 relative to the lowest price among the compared models | |
| Context window | Best: 1M | 200K | |
| Reasoning | No | No | |
| Open weights | No | No | |
| Cost / task | $0.0101 | — |
Intelligence
- GPT-5.6 Luna (Non-reasoning)
- Best: 15.5
- Claude 4.5 Haiku (Non-reasoning)
- 15.4
Coding
- GPT-5.6 Luna (Non-reasoning)
- 39.3
- Claude 4.5 Haiku (Non-reasoning)
- Best: 43.9
Math
- GPT-5.6 Luna (Non-reasoning)
- —
- Claude 4.5 Haiku (Non-reasoning)
- 39
Agentic
- GPT-5.6 Luna (Non-reasoning)
- Best: 13.4
- Claude 4.5 Haiku (Non-reasoning)
- 8
Speed
- GPT-5.6 Luna (Non-reasoning)
- Best: 118 t/s
- Claude 4.5 Haiku (Non-reasoning)
- 87.8 t/s
TTFT
- GPT-5.6 Luna (Non-reasoning)
- 0.76 s
- Claude 4.5 Haiku (Non-reasoning)
- Best: 0.5 s
Input · $ / 1M tokens
- GPT-5.6 Luna (Non-reasoning)
- Best: $0.20
- Claude 4.5 Haiku (Non-reasoning)
- $1×5 relative to the lowest price among the compared models
Output · $ / 1M tokens
- GPT-5.6 Luna (Non-reasoning)
- Best: $1.20
- Claude 4.5 Haiku (Non-reasoning)
- $5×4.2 relative to the lowest price among the compared models
Context window
- GPT-5.6 Luna (Non-reasoning)
- Best: 1M
- Claude 4.5 Haiku (Non-reasoning)
- 200K
Reasoning
- GPT-5.6 Luna (Non-reasoning)
- No
- Claude 4.5 Haiku (Non-reasoning)
- No
Open weights
- GPT-5.6 Luna (Non-reasoning)
- No
- Claude 4.5 Haiku (Non-reasoning)
- No
Cost / task
- GPT-5.6 Luna (Non-reasoning)
- $0.0101
- Claude 4.5 Haiku (Non-reasoning)
- —
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 (Non-reasoning)15.5 · $0.45
- Claude 4.5 Haiku (Non-reasoning)15.4 · $2