Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Grok 4.5 (High)
SpaceXSI
- Mistral Large 4 Preview
Mistral
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Grok 4.5 (High) SpaceXSI | Mistral Large 4 Preview Mistral | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | Best: 38.8 | 38.4 | |
| Coding | 72.4 | — | |
| Agentic | 41.2 | — | |
| Cyber Index | — | 49.5% | |
| Speed | 58.2 t/s | Best: 116 t/s | |
| TTFT | 10.6 s | Best: 1.46 s | |
| Input · $ / 1M tokens | $2×1.5 relative to the lowest price among the compared models | Best: $1.36 | |
| Output · $ / 1M tokens | $6×1.4 relative to the lowest price among the compared models | Best: $4.18 | |
| Context window | 500K | Best: 524K | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $0.881 | $1.13×1.3 relative to the lowest price among the compared models |
Intelligence
- Grok 4.5 (High)
- Best: 38.8
- Mistral Large 4 Preview
- 38.4
Coding
- Grok 4.5 (High)
- 72.4
- Mistral Large 4 Preview
- —
Agentic
- Grok 4.5 (High)
- 41.2
- Mistral Large 4 Preview
- —
Cyber Index
- Grok 4.5 (High)
- —
- Mistral Large 4 Preview
- 49.5%
Speed
- Grok 4.5 (High)
- 58.2 t/s
- Mistral Large 4 Preview
- Best: 116 t/s
TTFT
- Grok 4.5 (High)
- 10.6 s
- Mistral Large 4 Preview
- Best: 1.46 s
Input · $ / 1M tokens
- Grok 4.5 (High)
- $2×1.5 relative to the lowest price among the compared models
- Mistral Large 4 Preview
- Best: $1.36
Output · $ / 1M tokens
- Grok 4.5 (High)
- $6×1.4 relative to the lowest price among the compared models
- Mistral Large 4 Preview
- Best: $4.18
Context window
- Grok 4.5 (High)
- 500K
- Mistral Large 4 Preview
- Best: 524K
Reasoning
- Grok 4.5 (High)
- Yes
- Mistral Large 4 Preview
- Yes
Open weights
- Grok 4.5 (High)
- No
- Mistral Large 4 Preview
- No
Cost / task
- Grok 4.5 (High)
- Best: $0.881
- Mistral Large 4 Preview
- $1.13×1.3 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.
- Grok 4.5 (High)38.8 · $0.881
- Mistral Large 4 Preview38.4 · $1.13