# Is DeepSeek V3.2 SOTA?

As of Oct 14, 2026, DeepSeek V3.2 is ranked #71 in Factuality (since Oct 14, 2026; sources LMArena Text factuality; methodology v1.0).

Best current rank: #71 in Factuality, as of Oct 14, 2026.

As of Oct 14, 2026, DeepSeek V3.2 is ranked #71 in Factuality (since Oct 14, 2026; sources LMArena Text factuality; methodology v1.0). Ranked #71 in Factuality.

Methodology v1.0. Computed automatically.

- General LLM: RANKED #85 — Ranked #85 in General LLM.
- Reasoning: RANKED #79 — Ranked #79 in Reasoning.
- Math: INSUFFICIENT_DATA — #80 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath
- Coding: INSUFFICIENT_DATA — #92 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
- Coding › Web dev: RANKED #93 — Ranked #93 in Coding › Web dev.
- Long context: RANKED #82 — Ranked #82 in Long context.
- Factuality: RANKED #71 — Ranked #71 in Factuality.

## General LLM

https://isitsota.com/c/general-llm