⌕Is ___ SOTA?
isitsota / models / Moonshot AI / kimi-k2-thinking-turbo
VERIFIEDOct 142026
Is Kimi K2 Thinking Turbo state of the art?
It used to be.Was SOTA in Coding › Web dev.

As of Oct 14, 2026, Kimi K2 Thinking Turbo from Moonshot AI. Was SOTA in Coding › Web dev. Ranked #68 in Math.

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

The ruling, in plain English

Ranked #80 in General LLM.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
LMArena Text (style-controlled, overall)
kimi-k2-thinking-turbo
1430.0964424570184 1427.0–1433.22026-10-08INDEP.snap_368d64825bf4
LMArena Text (style-controlled, hard prompts)
kimi-k2-thinking-turbo
1453.2156273835678 1449.3–1457.12026-10-08INDEP.snap_368d64825bf4
LMArena Text (style-controlled, math)
kimi-k2-thinking-turbo
1436.1248392108314 1426.6–1445.72026-10-08INDEP.snap_368d64825bf4
GPQA Diamond
kimi-k2-thinking-turbo
0.8421717171717171 0.8–0.92025-11-06INDEP.snap_fee7890b5dd0
LMArena Text (style-controlled, coding)
kimi-k2-thinking-turbo
1486.5067209437384 1481.1–1491.92026-10-08INDEP.snap_368d64825bf4
LMArena WebDev
kimi-k2-thinking-turbo
1322.0763755812288 1314.7–1329.52026-10-08INDEP.snap_6949d6fb2488
LMArena Text (style-controlled, longer query)
kimi-k2-thinking-turbo
1433.228117531057 1428.3–1438.22026-10-08INDEP.snap_368d64825bf4
LMArena Text factuality
kimi-k2-thinking-turbo
1423.2380885403159 1420.4–1426.02026-10-08INDEP.snap_f051faf18005
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 · #80Ranked #80 in General LLM.
ReasoningNot SOTA · #77Ranked #77 in Reasoning.
MathNot SOTA · #68Ranked #68 in Math.
ScienceNot SOTA · #73Last listed at #73 in Science on 2025-11-06. That board does not award a crown.
CodingNot SOTA · #72Ranked #72 in Coding.
Coding › Web devNot SOTA · #92Ranked #92 in Coding › Web dev.
Long contextNot SOTA · #86Ranked #86 in Long context.
FactualityNot SOTA · #90Ranked #90 in Factuality.