DeepSeek V3.2 Thinking

DeepSeek‑V3.2 from DeepSeek harmonizes high computational efficiency with superior reasoning and agent performance. It builds on three main techniques: DeepSeek Sparse Attention for long‑context effi…

vercelAIGatewayCatalog/deepseek/deepseek-v3.2-thinking

DeepSeek‑V3.2 from DeepSeek harmonizes high computational efficiency with superior reasoning and agent performance. It builds on three main techniques: DeepSeek Sparse Attention for long‑context efficiency, a scalable reinforcement learning framework, and a large‑scale agentic task synthesis pipeline. This model excels at long-context reasoning and agentic tasks, efficiently handling extended inputs while maintaining strong accuracy. Its sparse attention design enables it to process complex, multi-step workflows without excessive compute costs. Overall, DeepSeek‑V3.2 targets long‑context reasoning, tool‑using agents, and efficient deployment in production environments.

Specifications & capabilities

Input
text
Output
text
Context window · tokens
128000
Max output · tokens
8000

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

32 / 100

source id
stanfordFMTI
canonical model id
vercelAIGatewayCatalog/deepseek/deepseek-v3.2-thinking
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
DeepSeek
assessment type
organization-level disclosure
metric
disclosure_score
result label
32 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Original sources

1–1 / 1

GitHub · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace