The Frontier · Intelligence · Entity
DeepSeek-V4-Flash
model · Model capabilities, AI infrastructure
| Metric | Value | Unit | As of | Origin | Verification | Context | Source | Evidence | Article |
|---|---|---|---|---|---|---|---|---|---|
| Relative single-token inference FLOPs vs baseline | 0.1 | ratio | — | paper | Reported (unverified) | DeepSeek-V4 efficiency at filled 1M context vs V3.2 | arXiv — DeepSeek-V4 (2606.19348) | Abstract / Figure 1 | deepseek-v4-attention-efficiency |
| Relative accumulated KV cache vs baseline | 0.07 | ratio | — | paper | Reported (unverified) | DeepSeek-V4 efficiency at filled 1M context vs V3.2 | arXiv — DeepSeek-V4 (2606.19348) | Abstract / Figure 1 | deepseek-v4-attention-efficiency |