# Is DeepSeek R1 SOTA?

**It used to be.** Was SOTA in General LLM.

As of Oct 14, 2026, DeepSeek R1 from DeepSeek. Was SOTA in General LLM. Was SOTA in Reasoning from 2025-04-05 to 2025-05-06. Currently ranked #115.

As of Oct 14, 2026. Methodology v1.0. Computed automatically.

- General LLM: WAS_SOTA #117 — Was SOTA in General LLM from 2025-01-28 to 2025-03-11. Currently ranked #117.
- Reasoning: WAS_SOTA #115 — Was SOTA in Reasoning from 2025-04-05 to 2025-05-06. Currently ranked #115.
- Math: INSUFFICIENT_DATA — #98 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath
- Science: RANKED #90 — Last listed at #90 in Science on 2025-01-20. That board does not award a crown.
- Coding: INSUFFICIENT_DATA — #116 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
- Long context: WAS_SOTA #121 — Was SOTA in Long context from 2025-02-11 to 2025-03-11. Currently ranked #121.
- Abstraction (ARC): RANKED #77 — Last listed at #77 in Abstraction (ARC) on 2025-01-20. That board does not award a crown.

## Reasoning

https://isitsota.com/c/reasoning