⌕Is ___ SOTA?
isitsota / models / Google DeepMind / gemini-3-flash-preview
VERIFIEDOct 142026
Is Gemini 3 Flash Preview state of the art?
No.Best recorded rank is #11 in Factuality.

As of Oct 14, 2026, Gemini 3 Flash Preview from Google DeepMind. Best recorded rank is #11 in Factuality. Last listed at #11 in Factuality on 2025-12-17.

Computed automaticallyas of Oct 14, 2026methodology v1.0confidence: low
ReasoningNot SOTA · #47#47 · 0dScienceNot SOTA · #47#47 · 0dCodingNot SOTA · #13#13 · 0dVisionNot SOTA · #32#32 · 0dVision · paretoNot SOTA · #32#32 · 0dFactualityNot SOTA · #11#11 · 0dAbstraction (ARC)Not SOTA · #36#36 · 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 #47 in Reasoning on 2025-12-17.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
GPQA Diamond
gemini-3-flash-preview_high · high
0.8939393939393939 0.9–0.92025-12-17INDEP.snap_e03cddec1fbb
SWE-bench Verified
gemini-3-flash-preview
0.7541322314049587 0.7–0.82025-12-17INDEP.snap_e03cddec1fbb
GDP.pdf
gemini-3-flash-preview_high · high
0.12025-12-17INDEP.snap_e03cddec1fbb
SimpleQA Verified
gemini-3-flash-preview_high · high
0.668 0.6–0.72025-12-17INDEP.snap_e03cddec1fbb
ARC-AGI
gemini-3-flash-preview
0.84672025-12-17INDEP.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 · #47Last listed at #47 in Reasoning on 2025-12-17.
ScienceNot SOTA · #47Last listed at #47 in Science on 2025-12-17. That board does not award a crown.
CodingNot SOTA · #13Last listed at #13 in Coding on 2025-12-17.
VisionNot SOTA · #32Ranked #32 in Vision.
FactualityNot SOTA · #11Last listed at #11 in Factuality on 2025-12-17.
Abstraction (ARC)Not SOTA · #36Last listed at #36 in Abstraction (ARC) on 2025-12-17. That board does not award a crown.