# Is Gemma 4 31B SOTA?

**Yes.** Yes on General LLM (≤32B); Reasoning (≤32B). Not the overall leader.

As of Oct 14, 2026, Gemma 4 31B from Google DeepMind. Yes on General LLM (≤32B); Reasoning (≤32B). Not the overall leader. Ranked #44 in Long context.

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

- General LLM: RANKED #54 — Ranked #54 in General LLM.
- Reasoning: RANKED #50 — Ranked #50 in Reasoning.
- Math: INSUFFICIENT_DATA — #40 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath
- Coding: INSUFFICIENT_DATA — #51 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
- Coding › Web dev: RANKED #78 — Ranked #78 in Coding › Web dev.
- Long context: RANKED #44 — Ranked #44 in Long context.
- Vision: INSUFFICIENT_DATA — #34 on LMArena Vision (style-controlled); missing GDP.pdf
- Factuality: RANKED #49 — Ranked #49 in Factuality.