VERIFIEDOct 142026
Is DeepSeek V4 Pro state of the art?
No.Best recorded rank is #28 in Science.
As of Oct 14, 2026, DeepSeek V4 Pro from DeepSeek. Best recorded rank is #28 in Science. Last listed at #28 in Science on 2026-04-24. That board does not award a crown.
General LLM#44 in this category#44 · 0dGeneral LLM · pareto#55 in this category#55 · 0dReasoning#45 in this category#45 · 0dReasoning · pareto#57 in this category#57 · 0dMathNot enough dataINSUFFICIENT_DATA · 0dScience#28 in this category#28 · 0dCodingNot enough dataINSUFFICIENT_DATA · 0dCoding › Web dev#55 in this category#55 · 0dCoding › Web dev · pareto#62 in this category#62 · 0dLong context#42 in this category#42 · 0d
Why
The ruling, in plain English
Ranked #44 in General LLM.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) deepseek-v4-pro | 1457.8484365293223 1453.9–1461.7 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| LMArena Text (style-controlled, hard prompts) deepseek-v4-pro | 1480.142757466783 1475.6–1484.7 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| LMArena Text (style-controlled, math) deepseek-v4-pro | 1444.8772318337224 1433.8–1456.0 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| GPQA Diamond deepseek-v4-pro_high · high | 0.9090909090909091 0.9–0.9 | 2026-04-24 | INDEP. | snap_fee7890b5dd0 |
| SWE-bench Verified deepseek-v4-pro_max · max | 0.7763975155279503 0.7–0.8 | 2026-04-24 | INDEP. | snap_fee7890b5dd0 |
| LMArena WebDev deepseek-v4-pro | 1446.815330354539 1440.5–1453.1 | 2026-10-13 | INDEP. | snap_c2cbd1c7f35e |
| LMArena Text (style-controlled, longer query) deepseek-v4-pro | 1471.8197265970673 1466.5–1477.1 | 2026-10-13 | INDEP. | snap_7d2d37f2ecb4 |
| LMArena Text factuality deepseek-v4-pro | 1454.8171352777495 1451.7–1458.0 | 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 | #44 in this category | Ranked #44 in General LLM. |
| Reasoning | #45 in this category | Ranked #45 in Reasoning. |
| Math | Not enough data | #61 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath |
| Science | #28 in this category | Last listed at #28 in Science on 2026-04-24. That board does not award a crown. |
| Coding | Not enough data | #6 on SWE-bench Verified; missing Terminal-Bench 4.0, SWE-bench Pro V2 HARD, and LMArena Text (style-controlled, coding) |
| Coding › Web dev | #55 in this category | Ranked #55 in Coding › Web dev. |
| Long context | #42 in this category | Ranked #42 in Long context. |
| Factuality | #41 in this category | Ranked #41 in Factuality. |