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 | 6.6 | 6.6 | |
| Coding | — | 9.5 | |
| Math | 4 | — | |
| Speed | 36.2 t/s | Best: 126 t/s | |
| TTFT | 2.04 s | Best: 0.75 s | |
| Input · $ / 1M tokens | $0.56×11.2 relative to the lowest price among the compared models | Best: $0.050 | |
| Output · $ / 1M tokens | $0.56×5.6 relative to the lowest price among the compared models | Best: $0.10 | |
| Context window | 128K | Best: 131K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Llama 3.1 Instruct 70B
- 6.6
- Granite 4.1 8B
- 6.6
Coding
- Llama 3.1 Instruct 70B
- —
- Granite 4.1 8B
- 9.5
Math
- Llama 3.1 Instruct 70B
- 4
- Granite 4.1 8B
- —
Speed
- Llama 3.1 Instruct 70B
- 36.2 t/s
- Granite 4.1 8B
- Best: 126 t/s
TTFT
- Llama 3.1 Instruct 70B
- 2.04 s
- Granite 4.1 8B
- Best: 0.75 s
Input · $ / 1M tokens
- Llama 3.1 Instruct 70B
- $0.56×11.2 relative to the lowest price among the compared models
- Granite 4.1 8B
- Best: $0.050
Output · $ / 1M tokens
- Llama 3.1 Instruct 70B
- $0.56×5.6 relative to the lowest price among the compared models
- Granite 4.1 8B
- Best: $0.10
Context window
- Llama 3.1 Instruct 70B
- 128K
- Granite 4.1 8B
- Best: 131K
Reasoning
- Llama 3.1 Instruct 70B
- No
- Granite 4.1 8B
- No
Open weights
- Llama 3.1 Instruct 70B
- Yes
- Granite 4.1 8B
- 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.
- Llama 3.1 Instruct 70B6.6 · $0.56
- Granite 4.1 8B6.6 · $0.063