⌕Is ___ SOTA?
isitsota / models / DeepSeek / deepseek-v4-1-flash
VERIFIEDOct 132026
Is DeepSeek V4.1 Flash state of the art?
No.Best recorded rank is #6 in Math.

As of Oct 13, 2026, DeepSeek V4.1 Flash from DeepSeek. Best recorded rank is #6 in Math. Last listed at #6 in Math on 2026-09-25.

Computed automaticallyas of Oct 13, 2026methodology v1.0confidence: low
ReasoningNot SOTA · #44#44 · 0dMathNot SOTA · #6#6 · 0dScienceNot SOTA · #44#44 · 0dVisionNot SOTA · #19#19 · 0dVision · paretoNot SOTA · #19#19 · 0dFactualityNot SOTA · #42#42 · 0d
Alert me if this changesGet badgeCompare with….mdJSON
View as of point-in-time crowns
Why

The ruling, in plain English

Last listed at #44 in Reasoning on 2026-09-09.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
GPQA Diamond
deepseek-v4.1-flash_max · max
0.8983585858585859 0.9–0.92026-09-09INDEP.snap_e03cddec1fbb
LMArena Text (style-controlled, math)
deepseek-v4.1-flash-max · max
1509.3869624489676 1477.9–1540.92026-09-25INDEP.snap_9a4e972507c9
GDP.pdf
deepseek-v4.1-flash_max · max
0.1982026-09-09INDEP.snap_e03cddec1fbb
SimpleQA Verified
deepseek-v4.1-flash_max · max
0.429 0.4–0.52026-09-09INDEP.snap_e03cddec1fbb
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
ReasoningNot SOTA · #44Last listed at #44 in Reasoning on 2026-09-09.
MathNot SOTA · #6Last listed at #6 in Math on 2026-09-25.
ScienceNot SOTA · #44Last listed at #44 in Science on 2026-09-09. That board does not award a crown.
VisionNot SOTA · #19Ranked #19 in Vision.
FactualityNot SOTA · #42Last listed at #42 in Factuality on 2026-09-09.