# Is DeepSeek V3 SOTA?

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

As of Oct 14, 2026, DeepSeek V3 from DeepSeek. Was SOTA in General LLM. Last listed at #11 in General LLM on 2025-03-17.

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

- General LLM: RANKED #11 — Last listed at #11 in General LLM on 2025-03-17.
- Reasoning: INSUFFICIENT_DATA — #11 on LMArena Text (style-controlled, hard prompts); missing Humanity's Last Exam and GPQA Diamond
- Math: INSUFFICIENT_DATA — #7 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath
- Science: RANKED #114 — Last listed at #114 in Science on 2024-12-26. That board does not award a crown.
- Coding: INSUFFICIENT_DATA — #10 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
- Long context: RANKED #142 — Ranked #142 in Long context.

## Coding

https://isitsota.com/c/coding