Back to Models

Deepseek v3.2 exp

DeepSeek V3.2 Exp is an experimental model featuring DeepSeek Sparse Attention (DSA) for high efficiency. It delivers long-context handling up to 128k tokens with reduced inference costs.

Parameters
685000000000 B
Context
163,840 tokens
Released
Invalid Date

Leaderboards

Performance vs. Industry Average

Intelligence

Deepseek v3.2 exp is of higher intelligence compared to average (4.1), with an intelligence score of 4.2.

Price

Deepseek v3.2 exp is cheaper compared to average ($1.68 per 1M Tokens) with a price of $0.12 per 1M Tokens.

Latency

Deepseek v3.2 exp has a higher average latency compared to average (53.05s), with an average latency of 99.52s.

P99 Latency

Deepseek v3.2 exp has a higher P99 latency compared to average (187.12s), taking 383.58s to receive the first token at P99 (TTFT).

Context Window

Deepseek v3.2 exp has a smaller context window than average (339k tokens), with a context window of 164k tokens.

Deepseek v3.2 exp - AutoBench