⌕Is ___ SOTA?
isitsota / models / Mistral / mistral-large-3
VERIFIEDOct 142026
Is Mistral Large 3 state of the art?
No.Best current rank is #68 in Vision.

As of Oct 14, 2026, Mistral Large 3 from Mistral. Best current rank is #68 in Vision. Ranked #68 in Vision.

Computed automaticallyas of Oct 14, 2026methodology v1.0confidence: low
General LLMNot SOTA · #103#103 · 0dReasoningNot SOTA · #104#104 · 0dMathNot SOTA · #110#110 · 0dCodingNot SOTA · #89#89 · 0dCoding › Web devNot SOTA · #102#102 · 0dLong contextNot SOTA · #103#103 · 0dVisionNot SOTA · #68#68 · 0dFactualityNot SOTA · #78#78 · 0d
Alert me if this changesGet badgeCompare with….mdJSON
View as of point-in-time crowns
Why

The ruling, in plain English

Ranked #103 in General LLM.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
LMArena Text (style-controlled, overall)
mistral-large-3
1413.7716548344843 1410.9–1416.72026-10-08INDEP.snap_368d64825bf4
LMArena Text (style-controlled, hard prompts)
mistral-large-3
1431.7556622069485 1428.2–1435.32026-10-08INDEP.snap_368d64825bf4
LMArena Text (style-controlled, math)
mistral-large-3
1400.3037791019615 1391.4–1409.22026-10-08INDEP.snap_368d64825bf4
LMArena Text (style-controlled, coding)
mistral-large-3
1470.281900136317 1465.5–1475.12026-10-08INDEP.snap_368d64825bf4
LMArena WebDev
mistral-large-3
1230.3680191474898 1204.9–1255.82026-10-08INDEP.snap_6949d6fb2488
LMArena Text (style-controlled, longer query)
mistral-large-3
1417.230374405935 1412.9–1421.62026-10-08INDEP.snap_368d64825bf4
LMArena Vision (style-controlled)
mistral-large-3
1199.757077684447 1191.8–1207.72026-10-09INDEP.snap_44d0155ee751
LMArena Text factuality
mistral-large-3
1433.50603177787 1431.0–1436.02026-10-08INDEP.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 · #103Ranked #103 in General LLM.
ReasoningNot SOTA · #104Ranked #104 in Reasoning.
MathNot SOTA · #110Ranked #110 in Math.
CodingNot SOTA · #89Ranked #89 in Coding.
Coding › Web devNot SOTA · #102Ranked #102 in Coding › Web dev.
Long contextNot SOTA · #103Ranked #103 in Long context.
VisionNot SOTA · #68Ranked #68 in Vision.
FactualityNot SOTA · #78Ranked #78 in Factuality.