⌕Is ___ SOTA?
isitsota / models / OpenAI / gpt-4-5-preview
VERIFIEDOct 142026
Is GPT-4.5 Preview state of the art?
It used to be.Was SOTA in General LLM.

As of Oct 14, 2026, GPT-4.5 Preview from OpenAI. Was SOTA in General LLM. Was SOTA in General LLM from 2025-10-17 to 2025-11-17. Currently ranked #62.

Computed automaticallyas of Oct 14, 2026methodology v1.0confidence: medium
General LLMWas SOTA#62 · 362dReasoningWas SOTA#92 · 557dMath#38 in this category#38 · 0dScience#92 in this category#92 · 0dCodingNot enough dataINSUFFICIENT_DATA · 0dLong contextWas SOTA#75 · 362dVisionNot enough dataINSUFFICIENT_DATA · 0dAbstraction (ARC)#83 in this category#83 · 0d
Follow changesGet badgeCompare with….mdJSON
View as of point-in-time crowns
Why

The ruling, in plain English

Was SOTA in General LLM from 2025-10-17 to 2025-11-17. Currently ranked #62.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
LMArena Text (style-controlled, overall)
gpt-4.5-preview-2025-02-27
1444.6078060524565 1438.9–1450.32026-10-13INDEP.snap_7d2d37f2ecb4
LMArena Text (style-controlled, hard prompts)
gpt-4.5-preview-2025-02-27
1440.1939634955104 1430.2–1450.22026-10-13INDEP.snap_7d2d37f2ecb4
Humanity's Last Exam
gpt-4.5-preview-2025-02-27
0.054400000000000004 0.0–0.12025-02-27INDEP.snap_fee7890b5dd0
GPQA Diamond
gpt-4.5-preview-2025-02-27
0.6868686868686869 0.6–0.82025-02-27INDEP.snap_fee7890b5dd0
LMArena Text (style-controlled, coding)
gpt-4.5-preview-2025-02-27
1457.9819396937069 1445.0–1471.02026-10-13INDEP.snap_7d2d37f2ecb4
LMArena Text (style-controlled, longer query)
gpt-4.5-preview-2025-02-27
1443.1940232525224 1429.6–1456.82026-10-13INDEP.snap_7d2d37f2ecb4
LMArena Vision (style-controlled)
gpt-4.5-preview-2025-02-27
1224.8818296052739 1213.2–1236.62026-10-09INDEP.snap_44d0155ee751
ARC-AGI
gpt-4.5-preview-2025-02-27
0.1032025-02-27INDEP.snap_fee7890b5dd0
Reign history

Where it sits in the succession

Full timeline →
General LLM
Claude 3.5 Sonnet
GPT-4O
O1 Preview
O1
DeepSeek R1
O1
GPT-4.5 Preview
O3
Gemini 2.5 Pro
Gemini 2.5 Pro
O3
Claude Opus 4.1
Gemini 2.5 Pro
GPT-5
Gemini 2.5 Pro
GPT-5
Gemini 2.5 Pro
Claude Sonnet 4.5
Gemini 2.5 Pro
Gemini 2.5 Pro
GPT-4.5 Preview
Gemini 3 Pro
Claude Opus 4.6
Gemini 3.1 Pro Preview
Claude Opus 4.6
Gemini 3.1 Pro Preview
GPT-5.4
Muse Spark
Claude Opus 4.6
Claude Opus 4.7
Gemini 3.1 Pro Preview
Muse Spark
Claude Opus 4.6
Claude Opus 4.7
Gemini 3.1 Pro Preview
GPT-5.5
Muse Spark
Claude Opus 4.6
Claude Opus 4.7
Gemini 3.1 Pro Preview
Muse Spark
Claude Opus 4.6
Claude Opus 4.7
Muse Spark
Claude Fable 5
Claude Opus 4.6
Claude Fable 5
Claude Opus 4.6
Muse Spark 1.1
Claude Fable 5
Claude Opus 5
Claude Fable 5
Claude Fable 5
Claude Opus 4.6
Muse Spark 1.2
Claude Fable 5
Claude Opus 4.6
Claude Opus 4.7
Muse Spark 1.2
Claude Fable 5
Claude Fable 5.1
Claude Opus 4.6
Claude Opus 4.7
Gemini 3.8 Flash
Muse Spark 1.2
Gemini 4 Argon
Reasoning
Claude 3.5 Sonnet
O1 Mini
O1 Preview
O1 Preview
Claude 3.5 Sonnet
O1 Preview
O1
O1 Preview
DeepSeek R1
O1
DeepSeek R1
O1
O3 Mini
DeepSeek R1
O1
DeepSeek R1
GPT-4.5 Preview
O1
DeepSeek R1
GPT-4.5 Preview
DeepSeek R1
DeepSeek V3 0324
GPT-4.5 Preview
O3
Claude Opus 4
O3
Gemini 2.5 Pro
Gemini 2.5 Pro
O3
Gemini 2.5 Pro
O3
Qwen3 235B A22b Instruct 2507
Claude Opus 4.1
Gemini 2.5 Pro
GPT-5
Qwen3 235B A22b Instruct 2507
Claude Opus 4.1
Gemini 2.5 Pro
GPT-5
Claude Opus 4.1
Claude Sonnet 4.5
Gemini 2.5 Pro
Gemini 3 Pro
Claude Opus 4.5
Gemini 3 Pro
Claude Opus 4.6
Gemini 3.1 Pro Preview
Claude Opus 4.6
Claude Opus 4.6
Muse Spark
Claude Opus 4.6
Claude Opus 4.7
Claude Opus 4.6
Claude Opus 4.6
Claude Opus 4.7
Claude Opus 4.6
Claude Fable 5
Claude Opus 4.6
Claude Opus 4.7
Claude Fable 5
Claude Opus 4.6
Claude Fable 5
Claude Opus 4.6
Claude Opus 5
Claude Fable 5
Claude Opus 4.6
Claude Fable 5
Claude Opus 4.6
Claude Opus 5
Claude Fable 5
Claude Opus 4.6
Claude Opus 4.7
Claude Fable 5
Claude Fable 5.1
Claude Opus 4.6
Claude Opus 4.7
Claude Opus 5.5
Gemini 4 Argon
Long context
O1
Claude 3.5 Sonnet
O1
O1 Preview
DeepSeek R1
Gemini 2.0 Flash 001
O1
DeepSeek R1
O1
Claude 3.7 Sonnet
GPT-4.5 Preview
GPT-4.5 Preview
DeepSeek V3 0324
GPT-4.5 Preview
DeepSeek V3 0324
GPT-4.1
GPT-4.5 Preview
DeepSeek V3 0324
GPT-4.1
GPT-4.5 Preview
O3
O3
Gemini 2.5 Pro
Gemini 2.5 Pro
O3
Claude Opus 4.1
Gemini 2.5 Pro
GPT-5
Gemini 2.5 Pro
GPT-5
Gemini 2.5 Pro
Claude Sonnet 4.5
Gemini 2.5 Pro
Gemini 2.5 Pro
GPT-4.5 Preview
Claude Sonnet 4.5
DeepSeek V3.2 Exp
Gemini 2.5 Pro
Gemini 3 Pro
Claude Opus 4.5
Claude Sonnet 4.5
Gemini 3 Pro
Claude Opus 4.6
Gemini 3.1 Pro Preview
Claude Opus 4.6
Claude Sonnet 4.6
Gemini 3.1 Pro Preview
Claude Opus 4.6
Gemini 3.1 Pro Preview
Claude Opus 4.6
Gemini 3.1 Pro Preview
GLM 5.1
Claude Opus 4.6
Claude Opus 4.7
Gemini 3.1 Pro Preview
Claude Opus 4.6
Claude Opus 4.7
Gemini 3.1 Pro Preview
GPT-5.5
Claude Opus 4.6
Claude Opus 4.7
GPT-5.5
Claude Opus 4.6
Claude Opus 4.7
Claude Opus 4.6
Claude Opus 4.7
Claude Opus 4.8
Claude Fable 5
Claude Opus 4.6
Claude Opus 4.7
Claude Opus 4.8
Claude Fable 5
Claude Opus 4.6
Claude Opus 4.7
Claude Fable 5
Claude Opus 4.6
Claude Opus 4.7
Kimi K3
Claude Fable 5
Claude Opus 4.6
Claude Opus 5
Kimi K3
Claude Fable 5
Claude Opus 4.6
Claude Opus 5
Muse Spark 1.2
Claude Fable 5
Claude Opus 4.6
Claude Opus 4.7
Claude Fable 5
Claude Fable 5.1
Claude Opus 4.6
Claude Opus 4.7
Gemini 3.8 Flash
Claude Opus 5.5
Gemini 4 Argon
Honest about the gaps

Where it is not the crown

CategoryThis modelWhy
General LLMWas SOTAWas SOTA in General LLM from 2025-10-17 to 2025-11-17. Currently ranked #62.
ReasoningWas SOTAWas SOTA in Reasoning from 2025-04-05 to 2025-05-06. Currently ranked #92.
Math#38 in this categoryRanked #38 in Math.
Science#92 in this categoryLast listed at #92 in Science on 2025-02-27. That board does not award a crown.
CodingNot enough data#102 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Long contextWas SOTAWas SOTA in Long context from 2025-10-17 to 2025-11-09. Currently ranked #75.
VisionNot enough data#57 on LMArena Vision (style-controlled); missing GDP.pdf
Abstraction (ARC)#83 in this categoryLast listed at #83 in Abstraction (ARC) on 2025-02-27. That board does not award a crown.