# Is GPT-5.5 SOTA?

**Close.** Near-SOTA in Factuality, rank #5.

As of Oct 14, 2026, GPT-5.5 from OpenAI. Near-SOTA in Factuality, rank #5. Close in Factuality: rank #5, 3.8 percentile points behind the leader.

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

- General LLM: WAS_SOTA #21 — Was SOTA in General LLM from 2026-04-28 to 2026-05-07. Currently ranked #21.
- Reasoning: RANKED #25 — Ranked #25 in Reasoning.
- Math: INSUFFICIENT_DATA — #13 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath
- Science: RANKED #30 — Last listed at #30 in Science on 2026-04-23. That board does not award a crown.
- Coding: INSUFFICIENT_DATA — #29 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
- Coding › Web dev: RANKED #42 — Ranked #42 in Coding › Web dev.
- Long context: WAS_SOTA #22 — Was SOTA in Long context from 2026-04-30 to 2026-05-14. Currently ranked #22.
- Vision: WAS_SOTA #10 — Was SOTA in Vision from 2026-07-08 to 2026-07-16. Currently ranked #10.
- Factuality: NEAR_SOTA #5 — Close in Factuality: rank #5, 3.8 percentile points behind the leader.
- Abstraction (ARC): RANKED #7 — Last listed at #7 in Abstraction (ARC) on 2026-04-23. That board does not award a crown.

## General LLM

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