⌕Is ___ SOTA?
isitsota / models / Google DeepMind / gemini-3-5-flash
VERIFIEDOct 132026
Is Gemini 3.5 Flash state of the art?
No.Best recorded rank is #3 in Coding.

As of Oct 13, 2026, Gemini 3.5 Flash from Google DeepMind. Best recorded rank is #3 in Coding. Last listed at #3 in Coding on 2026-05-19.

Computed automaticallyas of Oct 13, 2026methodology v1.0confidence: low
General LLMNot SOTA · #8#8 · 0dReasoningNot SOTA · #20#20 · 0dMathNot SOTA · #8#8 · 0dScienceNot SOTA · #20#20 · 0dCodingNot SOTA · #3#3 · 0dCoding › Web devNot SOTA · #7#7 · 0dVisionNot SOTA · #27#27 · 0dVision · paretoNot SOTA · #27#27 · 0dFactualityNot SOTA · #9#9 · 0dAbstraction (ARC)Not SOTA · #21#21 · 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 #8 in General LLM on 2026-07-02.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
LMArena Text (style-controlled, overall)
gemini-3.5-flash
1479.4578740598904 1473.7–1485.22026-07-02INDEP.snap_9a4e972507c9
GPQA Diamond
gemini-3.5-flash_high · high
0.928030303030303 0.9–1.02026-05-19INDEP.snap_e03cddec1fbb
LMArena Text (style-controlled, math)
gemini-3.5-flash-high · high
1503.6748684798786 1488.8–1518.52026-09-02INDEP.snap_9a4e972507c9
SWE-bench Verified
gemini-3.5-flash_high · high
0.7933884297520661 0.8–0.82026-05-19INDEP.snap_e03cddec1fbb
LMArena WebDev
gemini-3.5-flash
1506.3793096555328 1492.9–1519.92026-05-25INDEP.snap_d2f3c94c88f6
GDP.pdf
gemini-3.5-flash_medium · medium
0.142026-05-19INDEP.snap_e03cddec1fbb
LMArena Text factuality
gemini-3.5-flash-high · high
1479.3178820715902 1475.6–1483.12026-09-01INDEP.snap_d6425b45ea80
ARC-AGI
gemini-3.5-flash_high · high
0.9252026-05-19INDEP.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
General LLMNot SOTA · #8Last listed at #8 in General LLM on 2026-07-02.
ReasoningNot SOTA · #20Last listed at #20 in Reasoning on 2026-05-19.
MathNot SOTA · #8Last listed at #8 in Math on 2026-09-02.
ScienceNot SOTA · #20Last listed at #20 in Science on 2026-05-19. That board does not award a crown.
CodingNot SOTA · #3Last listed at #3 in Coding on 2026-05-19.
Coding › Web devNot SOTA · #7Last listed at #7 in Coding › Web dev on 2026-05-25.
VisionNot SOTA · #27Ranked #27 in Vision.
FactualityNot SOTA · #9Last listed at #9 in Factuality on 2026-09-01.