Llama 3.2 3B Instruct vs R1 1776
Meta vs Perplexity — benchmarks, pricing, and capabilities side by side.
- •R1 1776 has the higher intelligence index (95.4 vs 30.8)
- •R1 1776 is cheaper ($0.00 vs $0.05 per 1M input)
| Llama 3.2 3B Instruct | R1 1776 | |
|---|---|---|
| Intelligence index | 30.8 | 95.4 |
| Developer | Meta | Perplexity |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 131,072 tokens | — |
| Input price | $0.05 / 1M | $0.00 / 1M |
| Output price | $0.34 / 1M | $0.00 / 1M |
| Speed | 172 tok/s | — |
| Released | September 25, 2024 | February 18, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
Llama 3.2 3B Instruct
R1 1776
MATH-500
48.9
95.4