Model Comparator
Compare up to four models using the same criteria.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | Best: 18.5 | 18.4 | |
| Coding | — | 48.2 | |
| Agentic | — | 8.3 | |
| Speed | Best: 111 t/s | 55.9 t/s | |
| TTFT | Best: 0.94 s | 2.5 s | |
| Input · $ / 1M tokens | Best: $0.10 | $0.60×6 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.50 | $3.60×7.2 relative to the lowest price among the compared models | |
| Context window | Best: 1M | 262K | |
| Reasoning | No | Yes | |
| Open weights | No | Yes | |
| Cost / task | Best: $0.0113 | $0.475×42 relative to the lowest price among the compared models |
Intelligence
- GPT-6 Luna (Non-reasoning)
- Best: 18.5
- Qwen3.5 397B A17B (Reasoning)
- 18.4
Coding
- GPT-6 Luna (Non-reasoning)
- —
- Qwen3.5 397B A17B (Reasoning)
- 48.2
Agentic
- GPT-6 Luna (Non-reasoning)
- —
- Qwen3.5 397B A17B (Reasoning)
- 8.3
Speed
- GPT-6 Luna (Non-reasoning)
- Best: 111 t/s
- Qwen3.5 397B A17B (Reasoning)
- 55.9 t/s
TTFT
- GPT-6 Luna (Non-reasoning)
- Best: 0.94 s
- Qwen3.5 397B A17B (Reasoning)
- 2.5 s
Input · $ / 1M tokens
- GPT-6 Luna (Non-reasoning)
- Best: $0.10
- Qwen3.5 397B A17B (Reasoning)
- $0.60×6 relative to the lowest price among the compared models
Output · $ / 1M tokens
- GPT-6 Luna (Non-reasoning)
- Best: $0.50
- Qwen3.5 397B A17B (Reasoning)
- $3.60×7.2 relative to the lowest price among the compared models
Context window
- GPT-6 Luna (Non-reasoning)
- Best: 1M
- Qwen3.5 397B A17B (Reasoning)
- 262K
Reasoning
- GPT-6 Luna (Non-reasoning)
- No
- Qwen3.5 397B A17B (Reasoning)
- Yes
Open weights
- GPT-6 Luna (Non-reasoning)
- No
- Qwen3.5 397B A17B (Reasoning)
- Yes
Cost / task
- GPT-6 Luna (Non-reasoning)
- Best: $0.0113
- Qwen3.5 397B A17B (Reasoning)
- $0.475×42 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-6 Luna (Non-reasoning)18.5 · $0.0113
- Qwen3.5 397B A17B (Reasoning)18.4 · $0.475