VERIFIEDOct 142026
Is DeepSeek V3.2 state of the art?
No.Best current rank is #71 in Factuality.
As of Oct 14, 2026, DeepSeek V3.2 from DeepSeek. Best current rank is #71 in Factuality. Ranked #71 in Factuality.
General LLM#84 in this category#84 · 0dGeneral LLM · pareto#112 in this category#112 · 0dReasoning#78 in this category#78 · 0dReasoning · pareto#104 in this category#104 · 0dMathNot enough dataINSUFFICIENT_DATA · 0dCodingNot enough dataINSUFFICIENT_DATA · 0dCoding › Web dev#91 in this category#91 · 0dCoding › Web dev · pareto#104 in this category#104 · 0dLong context#81 in this category#81 · 0dLong context · pareto#102 in this category#102 · 0d
Why
The ruling, in plain English
Ranked #84 in General LLM.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) deepseek-v3.2 | 1424.6682980750716 1421.2–1428.2 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| LMArena Text (style-controlled, hard prompts) deepseek-v3.2 | 1447.1292069169506 1442.7–1451.6 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| LMArena Text (style-controlled, math) deepseek-v3.2 | 1426.7272795014242 1416.1–1437.4 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| LMArena Text (style-controlled, coding) deepseek-v3.2 | 1469.3630651513108 1463.1–1475.6 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| LMArena WebDev deepseek-v3.2 | 1325.7274076035285 1317.8–1333.7 | 2026-10-13 | INDEP. | snap_c2cbd1c7f35e |
| LMArena Text (style-controlled, longer query) deepseek-v3.2 | 1440.5548516277652 1434.8–1446.3 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| LMArena Text factuality deepseek-v3.2 | 1436.7888706191532 1433.6–1440.0 | 2026-10-13 | INDEP. | snap_af980e7d8ae9 |
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 | #84 in this category | Ranked #84 in General LLM. |
| Reasoning | #78 in this category | Ranked #78 in Reasoning. |
| Math | Not enough data | #79 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath |
| Coding | Not enough data | #90 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD |
| Coding › Web dev | #91 in this category | Ranked #91 in Coding › Web dev. |
| Long context | #81 in this category | Ranked #81 in Long context. |
| Factuality | #71 in this category | Ranked #71 in Factuality. |