VERIFIEDOct 132026
Is DeepSeek V3.1 state of the art?
It used to be.Was SOTA in General LLM.
As of Oct 13, 2026, DeepSeek V3.1 from DeepSeek. Was SOTA in General LLM. Last listed at #6 in Math on 2025-09-08.
Why
The ruling, in plain English
Last listed at #7 in General LLM on 2025-08-28.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) deepseek-v3.1 | 1419.277867669684 1410.7–1427.9 | 2025-08-28 | INDEP. | snap_9a4e972507c9 |
| LMArena Text (style-controlled, math) deepseek-v3.1 | 1445.2134731391786 1420.9–1469.5 | 2025-09-08 | INDEP. | snap_9a4e972507c9 |
| LMArena Text (style-controlled, longer query) deepseek-v3.1 | 1420.6565063485457 1413.6–1427.7 | 2025-09-08 | INDEP. | snap_9a4e972507c9 |
Reign history
Where it sits in the succession
No closed or open crown interval includes this model.
Honest about the gaps
Where it is not the crown
| Category | This model | Why |
|---|---|---|
| General LLM | Not SOTA · #7 | Last listed at #7 in General LLM on 2025-08-28. |
| Math | Not SOTA · #6 | Last listed at #6 in Math on 2025-09-08. |
| Long context | Not SOTA · #7 | Last listed at #7 in Long context on 2025-09-08. |