GPT-5.6 Luna (Max) vs Hy3
GPT-5.6 Luna (Max) scores 37.3 on the Artificial Analysis Intelligence Index, against 25.3 for Hy3. Hy3 costs $0.241 per million tokens (3:1 blend), against $0.45 for GPT-5.6 Luna (Max). GPT-5.6 Luna (Max) generates 107 t/s, against 93.1 t/s for Hy3. Both accept a context of 1M tokens.
Comparison generated from the catalogue data. Add or remove models below to refine it.
2 models compared
- GPT-5.6 Luna (Max)
OpenAI
- Hy3
Tencent
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.6 Luna (Max) OpenAI | Hy3 Tencent | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 37.3 | 25.3 | |
| Coding | Best: 71.4 | 58.8 | |
| Agentic | Best: 42.1 | 24.1 | |
| Speed | Best: 107 t/s | 93.1 t/s | |
| TTFT | 144 s | Best: 2.89 s | |
| Input · $ / 1M tokens | $0.20×1.5 relative to the lowest price among the compared models | Best: $0.136 | |
| Output · $ / 1M tokens | $1.20×2.2 relative to the lowest price among the compared models | Best: $0.555 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes | |
| Cost / task | $0.178×2.5 relative to the lowest price among the compared models | Best: $0.0724 |
Intelligence
- GPT-5.6 Luna (Max)
- Best: 37.3
- Hy3
- 25.3
Coding
- GPT-5.6 Luna (Max)
- Best: 71.4
- Hy3
- 58.8
Agentic
- GPT-5.6 Luna (Max)
- Best: 42.1
- Hy3
- 24.1
Speed
- GPT-5.6 Luna (Max)
- Best: 107 t/s
- Hy3
- 93.1 t/s
TTFT
- GPT-5.6 Luna (Max)
- 144 s
- Hy3
- Best: 2.89 s
Input · $ / 1M tokens
- GPT-5.6 Luna (Max)
- $0.20×1.5 relative to the lowest price among the compared models
- Hy3
- Best: $0.136
Output · $ / 1M tokens
- GPT-5.6 Luna (Max)
- $1.20×2.2 relative to the lowest price among the compared models
- Hy3
- Best: $0.555
Context window
- GPT-5.6 Luna (Max)
- 1M
- Hy3
- 1M
Reasoning
- GPT-5.6 Luna (Max)
- Yes
- Hy3
- Yes
Open weights
- GPT-5.6 Luna (Max)
- No
- Hy3
- Yes
Cost / task
- GPT-5.6 Luna (Max)
- $0.178×2.5 relative to the lowest price among the compared models
- Hy3
- Best: $0.0724
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
- Hy325.3 · $0.0724