Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Grok 4
SpaceXSI
- Hy3-preview (Reasoning)
Tencent
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Grok 4 SpaceXSI | Hy3-preview (Reasoning) Tencent | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 22.5 | Best: 22.7 | |
| Coding | — | 58.8 | |
| Math | 92.7 | — | |
| Agentic | — | 24.1 | |
| Speed | 74 t/s | — | |
| TTFT | 12.6 s | — | |
| Input · $ / 1M tokens | $3×47.6 relative to the lowest price among the compared models | Best: $0.063 | |
| Output · $ / 1M tokens | $15×71.4 relative to the lowest price among the compared models | Best: $0.21 | |
| Context window | 256K | 256K | |
| Reasoning | Yes | Yes | |
| Open weights | No | Yes |
Intelligence
- Grok 4
- 22.5
- Hy3-preview (Reasoning)
- Best: 22.7
Coding
- Grok 4
- —
- Hy3-preview (Reasoning)
- 58.8
Math
- Grok 4
- 92.7
- Hy3-preview (Reasoning)
- —
Agentic
- Grok 4
- —
- Hy3-preview (Reasoning)
- 24.1
Speed
- Grok 4
- 74 t/s
- Hy3-preview (Reasoning)
- —
TTFT
- Grok 4
- 12.6 s
- Hy3-preview (Reasoning)
- —
Input · $ / 1M tokens
- Grok 4
- $3×47.6 relative to the lowest price among the compared models
- Hy3-preview (Reasoning)
- Best: $0.063
Output · $ / 1M tokens
- Grok 4
- $15×71.4 relative to the lowest price among the compared models
- Hy3-preview (Reasoning)
- Best: $0.21
Context window
- Grok 4
- 256K
- Hy3-preview (Reasoning)
- 256K
Reasoning
- Grok 4
- Yes
- Hy3-preview (Reasoning)
- Yes
Open weights
- Grok 4
- No
- Hy3-preview (Reasoning)
- Yes
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.
- Grok 422.5 · $6
- Hy3-preview (Reasoning)22.7 · $0.10