by ·
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
| Signal | Strength | Weight | Impact |
|---|---|---|---|
| Benchmarksjust now | 71 | 30% | +21.3 |
| Pricingjust now | 100 | 15% | +15.0 |
| Recencyjust now | 100 | 15% | +15.0 |
| Capabilitiesjust now | 67 | 20% | +13.3 |
| Context Windowjust now | 96 | 10% | +9.6 |
| Output Capacityjust now | 93 | 10% | +9.3 |
LMSYS Arena Elo
1433
Percentile
88.8
Weight
30%
No task benchmark data available yet for this model.
View this model against the provider’s recent shipping cadence.
Community and practitioner feedback adds real-world signal on top of benchmarks and pricing.
Share your experience with DeepSeek V4 Flash and help the community make better decisions.
LMSYS Arena Elo
1433
Percentile
88.8
Weight
30%
No task benchmark data available yet for this model.
Cost Estimator
You save $44.42/month vs category average