⌕Is ___ SOTA?
isitsota / models / OpenAI / o4-mini
VERIFIEDOct 132026
Is O4 Mini state of the art?
It used to be.Was SOTA in Math.

As of Oct 13, 2026, O4 Mini from OpenAI. Was SOTA in Math. Was SOTA in Math from 2025-07-20 to 2025-09-29. Currently ranked #21.

Computed automaticallyas of Oct 13, 2026methodology v1.0confidence: medium
General LLMNot SOTA · #9#9 · 0dReasoningNot SOTA · #9#9 · 0dMathWas SOTA#21 · 450dMath · paretoNot SOTA · #21#21 · 0dScienceNot SOTA · #88#88 · 0dCodingNot SOTA · #9#9 · 0dLong contextNot SOTA · #9#9 · 0dVisionNot SOTA · #6#6 · 0dFactualityNot SOTA · #71#71 · 0dAbstraction (ARC)Not SOTA · #52#52 · 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 #9 in General LLM on 2025-07-07.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
LMArena Text (style-controlled, overall)
o4-mini-2025-04-16
1398.8655225189248 1394.8–1403.72025-07-07INDEP.snap_9a4e972507c9
LMArena Text (style-controlled, hard prompts)
o4-mini-2025-04-16
1395.5184941584143 1388.5–1404.72025-06-11INDEP.snap_9a4e972507c9
Humanity's Last Exam
o4-mini-2025-04-16_high · high
0.1808 0.2–0.22025-04-16INDEP.snap_e03cddec1fbb
GPQA Diamond
o4-mini-2025-04-16_high · high
0.7960858585858586 0.7–0.82025-04-16INDEP.snap_e03cddec1fbb
LMArena Text (style-controlled, coding)
o4-mini-2025-04-16
1423.120453965176 1413.9–1433.12025-06-18INDEP.snap_9a4e972507c9
LMArena Text (style-controlled, longer query)
o4-mini-2025-04-16
1399.6988385427683 1395.2–1405.02025-07-07INDEP.snap_9a4e972507c9
LMArena Vision (style-controlled)
o4-mini-2025-04-16
1196.6721555841782 1186.7–1206.72025-09-30INDEP.snap_ae2e1c2545e6
SimpleQA Verified
o4-mini-2025-04-16_low · low
0.196 0.2–0.22025-04-16INDEP.snap_e03cddec1fbb
ARC-AGI
o4-mini-2025-04-16_high · high
0.58672025-04-16INDEP.snap_e03cddec1fbb
Reign history

Where it sits in the succession

Full timeline →
Math
Gemini 1.5 Pro 002
Gemini 2.5 Pro Exp 03.25
Gemini 2.5 Pro Exp 03.25
O3
O4 Mini
Gemini 2.5 Pro Exp 03.25
Gemini 2.5 Pro Preview 05.06
O3
O4 Mini
Gemini 2.5 Pro Exp 03.25
Gemini 2.5 Pro Preview 05.06
Gemini 2.5 Pro Preview 06.05
O3
O4 Mini
Gemini 2.5 Pro Preview 06.05
GPT-5
GPT-5 Mini
O3
GPT-5
GPT-5 Pro
Gemini 3 Pro Preview
GPT-5 Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview
GPT-5.4 Pro
Muse Spark
Honest about the gaps

Where it is not the crown

CategoryThis modelWhy
General LLMNot SOTA · #9Last listed at #9 in General LLM on 2025-07-07.
ReasoningNot SOTA · #9Last listed at #9 in Reasoning on 2025-06-11.
MathWas SOTAWas SOTA in Math from 2025-07-20 to 2025-09-29. Currently ranked #21.
ScienceNot SOTA · #88Last listed at #88 in Science on 2025-04-16. That board does not award a crown.
CodingNot SOTA · #9Last listed at #9 in Coding on 2025-06-18.
Long contextNot SOTA · #9Last listed at #9 in Long context on 2025-07-07.
VisionNot SOTA · #6Last listed at #6 in Vision on 2025-09-30.
FactualityNot SOTA · #71Last listed at #71 in Factuality on 2025-04-16.