Back to Models

Deepseek v3.1

DeepSeek-V3.1 is a hybrid reasoning model (671B params, 37B active) supporting thinking and non-thinking modes. It improves on V3 with better tool use, code generation, and reasoning efficiency.

Parameters
671000000000 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 v3.1 has a smaller context window than average (406k tokens), with a context window of 164k tokens.

Deepseek v3.1 - AutoBench