DeepSeek V3.2 Speciale vs Reka Flash 3
DeepSeek vs Reka AI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 56.2)
- •Reka Flash 3 is cheaper ($0.10 vs $0.29 per 1M input)
- •DeepSeek V3.2 Speciale has a larger context window (164K)
| DeepSeek V3.2 Speciale | Reka Flash 3 | |
|---|---|---|
| Intelligence index | 89.9 | 56.2 |
| Developer | DeepSeek | Reka AI |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | 65,536 tokens |
| Input price | $0.29 / 1M | $0.10 / 1M |
| Output price | $0.43 / 1M | $0.20 / 1M |
| Speed | — | 93 tok/s |
| Released | December 1, 2025 | March 12, 2025 |
| Parameters | — | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek V3.2 Speciale
Reka Flash 3
AIME 2025
96.7
33.7
GPQA Diamond
87.1
52.9
Humanity’s Last Exam
26.1
5.1
LiveCodeBench
89.6
43.5
MMLU-Pro
86.3
66.9