DeepSeek V3 0324
DeepSeek MoE model with 671B parameters (37B active) and 128K context for general tasks
Leaderboards
QUALITY
Average Score combining domain-specific Autobench scores; Higher is better
- 3.95
- 4.51
- 4.49
- 4.48
- 4.42
- 4.41
- 4.33
- 4.32
- 4.31
- 4.27
- 4.24
- 4.18
- 4.18
- 4.18
- 4.17
- 4.17
- 4.06
- 3.98
- 3.98
- 3.95
- 3.88
- 3.66
- 3.64
- 3.59
- 3.54
- 3.49
PRICE
USD cent per average answer; Lower is better
- 0.12
- 0.02
- 0.02
- 0.03
- 0.05
- 0.08
- 0.08
- 0.09
- 0.14
- 0.18
- 0.24
- 0.24
- 0.36
- 0.45
- 0.63
- 0.63
- 0.64
- 0.83
- 0.87
- 0.91
- 1.59
- 1.71
- 1.85
- 2.92
- 4.37
- 9.13
LATENCY
Average Latency in Seconds; Lower is better
- 40.3s
- 5.29s
- 7.53s
- 7.74s
- 10.65s
- 11.52s
- 17.54s
- 19.16s
- 24.36s
- 26.12s
- 27.01s
- 29.72s
- 32.86s
- 33.67s
- 39.05s
- 48.62s
- 48.71s
- 60.96s
- 61.12s
- 63.9s
- 65.02s
- 65.03s
- 65.9s
- 66.5s
- 68.34s
- 72.64s
- 80.74s
- 90s
- 119.17s
Performance vs. Industry Average
Intelligence
DeepSeek V3 0324 is of lower intelligence compared to average (4.1), with an intelligence score of 3.9.
Price
DeepSeek V3 0324 is cheaper compared to average ($0.91 per 1M Tokens) with a price of $0.12 per 1M Tokens.
Latency
DeepSeek V3 0324 has a lower average latency compared to average (45.24s), with an average latency of 40.30s.
P99 Latency
DeepSeek V3 0324 has a higher P99 latency compared to average (172.60s), taking 199.71s to receive the first token at P99 (TTFT).
Context Window
DeepSeek V3 0324 has a smaller context window than average (246k tokens), with a context window of 128k tokens.