Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Llama 4 Scout
Meta
- DeepSeek R1 Distill Llama 8B
DeepSeek
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Llama 4 Scout Meta | DeepSeek R1 Distill Llama 8B DeepSeek | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 6.5 | 6.5 | |
| Coding | 8.2 | — | |
| Math | 14 | Best: 41.3 | |
| Agentic | 0.5 | — | |
| Speed | 67.6 t/s | — | |
| TTFT | 0.95 s | — | |
| Input · $ / 1M tokens | $0.18 | — | |
| Output · $ / 1M tokens | $0.66 | — | |
| Context window | Best: 10M | 128K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.112 | — |
Intelligence
- Llama 4 Scout
- 6.5
- DeepSeek R1 Distill Llama 8B
- 6.5
Coding
- Llama 4 Scout
- 8.2
- DeepSeek R1 Distill Llama 8B
- —
Math
- Llama 4 Scout
- 14
- DeepSeek R1 Distill Llama 8B
- Best: 41.3
Agentic
- Llama 4 Scout
- 0.5
- DeepSeek R1 Distill Llama 8B
- —
Speed
- Llama 4 Scout
- 67.6 t/s
- DeepSeek R1 Distill Llama 8B
- —
TTFT
- Llama 4 Scout
- 0.95 s
- DeepSeek R1 Distill Llama 8B
- —
Input · $ / 1M tokens
- Llama 4 Scout
- $0.18
- DeepSeek R1 Distill Llama 8B
- —
Output · $ / 1M tokens
- Llama 4 Scout
- $0.66
- DeepSeek R1 Distill Llama 8B
- —
Context window
- Llama 4 Scout
- Best: 10M
- DeepSeek R1 Distill Llama 8B
- 128K
Reasoning
- Llama 4 Scout
- No
- DeepSeek R1 Distill Llama 8B
- Yes
Open weights
- Llama 4 Scout
- Yes
- DeepSeek R1 Distill Llama 8B
- Yes
Cost / task
- Llama 4 Scout
- $0.112
- DeepSeek R1 Distill Llama 8B
- —
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 4 Scout6.5 · $0.112
Not plotted for lack of data on these axes: DeepSeek R1 Distill Llama 8B.