DeepSeek-V4-Flash vs Llama 3.3 70B Instruct
DeepSeek vs Meta — benchmarks, pricing, and capabilities side by side.
- •DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 50.6)
- •Llama 3.3 70B Instruct is faster
- •DeepSeek-V4-Flash has a larger context window (1M)
| DeepSeek-V4-Flash | Llama 3.3 70B Instruct | |
|---|---|---|
| Intelligence index | 89.4 | 50.6 |
| Developer | DeepSeek | Meta |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 1,048,576 tokens | 131,072 tokens |
| Input price | $0.10 / 1M | $0.10 / 1M |
| Output price | $0.20 / 1M | $0.32 / 1M |
| Speed | 109 tok/s | 2220 tok/s |
| Released | April 24, 2026 | December 6, 2024 |
| Parameters | 284B (13B active) | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek-V4-Flash
Llama 3.3 70B Instruct
GPQA Diamond
89.4
50.5
Humanity’s Last Exam
32.1
4