# Is DeepSeek V4 Pro Preview SOTA?

Best current rank: #66 in Long context, as of Nov 22, 2026.

As of Nov 22, 2026, DeepSeek V4 Pro Preview is ranked #66 in Long context (since Nov 22, 2026; sources LMArena Text (style-controlled, longer query); methodology v1.0). Ranked #66 in Long context.

Canonical: https://isitsota.com/m/deepseek-v4-pro-preview/math
Last updated: 2026-11-22
Methodology v1.0. Computed automatically.

- General LLM: #67 in General LLM — Ranked #67 in General LLM.
- Reasoning: #72 in Reasoning — Ranked #72 in Reasoning.
- Math: Not enough data — #53 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath
- Coding: Not enough data — #93 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
- Coding › Web dev: #73 in Coding › Web dev — Ranked #73 in Coding › Web dev.
- Long context: #66 in Long context — Ranked #66 in Long context.
- Factuality: #69 in Factuality — Ranked #69 in Factuality.

## Math

https://isitsota.com/c/math

### Primary benchmarks

- LMArena Text (style-controlled, math): 1465 (CI 1453–1477) on Nov 19, 2026 (#63 of 231).

## Related

- Model page: https://isitsota.com/m/deepseek-v4-pro-preview.md
- Lab: [DeepSeek](https://isitsota.com/labs/deepseek.md)
- Category: [General LLM](https://isitsota.com/c/general-llm.md)
- Category: [Reasoning](https://isitsota.com/c/reasoning.md)
- Category: [Math](https://isitsota.com/c/math.md)
- Category: [Coding](https://isitsota.com/c/coding.md)
- Category: [Coding › Web dev](https://isitsota.com/c/coding-web-dev.md)
- Category: [Long context](https://isitsota.com/c/long-context.md)
- Category: [Factuality](https://isitsota.com/c/factuality.md)
- JSON: https://api.isitsota.com/v1/models/deepseek-v4-pro-preview
