⌕Is ___ SOTA?
isitsota / models / DeepSeek / deepseek-v4-pro-high-preview
VERIFIEDOct 142026
Is DeepSeek V4 Pro High Preview state of the art?
No.Best current rank is #50 in Long context.

As of Oct 14, 2026, DeepSeek V4 Pro High Preview from DeepSeek. Best current rank is #50 in Long context. Ranked #50 in Long context.

Computed automaticallyas of Oct 14, 2026methodology v1.0confidence: medium
View as of point-in-time crowns
Why

The ruling, in plain English

Ranked #51 in General LLM.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
LMArena Text (style-controlled, overall)
deepseek-v4-pro-high-preview
1454.8142034029117 1450.9–1458.82026-10-13INDEP.snap_7d2d37f2ecb4
LMArena Text (style-controlled, hard prompts)
deepseek-v4-pro-high-preview
1473.690987779089 1469.0–1478.32026-10-13INDEP.snap_7d2d37f2ecb4
LMArena Text (style-controlled, math)
deepseek-v4-pro-high-preview
1465.667920419507 1453.9–1477.42026-10-13INDEP.snap_7d2d37f2ecb4
LMArena Text (style-controlled, coding)
deepseek-v4-pro-high-preview
1488.1245988251885 1482.0–1494.22026-10-13INDEP.snap_7d2d37f2ecb4
LMArena WebDev
deepseek-v4-pro-high-preview
1463.8491323105375 1457.5–1470.22026-10-13INDEP.snap_c2cbd1c7f35e
LMArena Text (style-controlled, longer query)
deepseek-v4-pro-high-preview
1464.818734338734 1459.4–1470.22026-10-13INDEP.snap_7d2d37f2ecb4
LMArena Text factuality
deepseek-v4-pro-high-preview
1447.4498991646292 1444.3–1450.62026-10-13INDEP.snap_af980e7d8ae9
Reign history

Where it sits in the succession

Full timeline →

No closed or open crown interval includes this model.

Honest about the gaps

Where it is not the crown

CategoryThis modelWhy
General LLM#51 in this categoryRanked #51 in General LLM.
Reasoning#56 in this categoryRanked #56 in Reasoning.
MathNot enough data#44 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath
CodingNot enough data#70 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Coding › Web dev#52 in this categoryRanked #52 in Coding › Web dev.
Long context#50 in this categoryRanked #50 in Long context.
Factuality#52 in this categoryRanked #52 in Factuality.