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

Average Score combining domain-specific Autobench scores; Higher is better

Performance vs. Industry Average

Context Window

Deepseek v3.2 exp has a smaller context window than average (406k tokens), with a context window of 164k tokens.

Deepseek v3.2 exp - AutoBench