Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Hy3-preview (Non-reasoning)
Tencent
- GPT-5 mini (High)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Hy3-preview (Non-reasoning) Tencent | GPT-5 mini (High) OpenAI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 17 | 16.8 | |
| Coding | — | 15.6 | |
| Math | — | 90.7 | |
| Agentic | — | 6.8 | |
| Speed | — | 147 t/s | |
| TTFT | — | 49.5 s | |
| Input · $ / 1M tokens | Best: $0.063 | $0.25×4 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.21 | $2×9.5 relative to the lowest price among the compared models | |
| Context window | 256K | Best: 400K | |
| Reasoning | No | Yes | |
| Open weights | Yes | No | |
| Cost / task | — | $0.0535 |
Intelligence
- Hy3-preview (Non-reasoning)
- Best: 17
- GPT-5 mini (High)
- 16.8
Coding
- Hy3-preview (Non-reasoning)
- —
- GPT-5 mini (High)
- 15.6
Math
- Hy3-preview (Non-reasoning)
- —
- GPT-5 mini (High)
- 90.7
Agentic
- Hy3-preview (Non-reasoning)
- —
- GPT-5 mini (High)
- 6.8
Speed
- Hy3-preview (Non-reasoning)
- —
- GPT-5 mini (High)
- 147 t/s
TTFT
- Hy3-preview (Non-reasoning)
- —
- GPT-5 mini (High)
- 49.5 s
Input · $ / 1M tokens
- Hy3-preview (Non-reasoning)
- Best: $0.063
- GPT-5 mini (High)
- $0.25×4 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Hy3-preview (Non-reasoning)
- Best: $0.21
- GPT-5 mini (High)
- $2×9.5 relative to the lowest price among the compared models
Context window
- Hy3-preview (Non-reasoning)
- 256K
- GPT-5 mini (High)
- Best: 400K
Reasoning
- Hy3-preview (Non-reasoning)
- No
- GPT-5 mini (High)
- Yes
Open weights
- Hy3-preview (Non-reasoning)
- Yes
- GPT-5 mini (High)
- No
Cost / task
- Hy3-preview (Non-reasoning)
- —
- GPT-5 mini (High)
- $0.0535
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.
- Hy3-preview (Non-reasoning)17 · $0.10
- GPT-5 mini (High)16.8 · $0.688