Noometry

Model comparison

GPT-4.5 vs GPT-5.1

GPT-5.1 is the stronger model overall, scoring 49.0 to 37.2 on the Noometry Index.

Last verified . 35 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

GPT-5.1 OpenAI

49.0

Rank #53 Confirmed

Summary

  • They share 35 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and GPT-5.1 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.1 leads 39.8 to 13.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 10.3% for GPT-4.5 and 72.8% for GPT-5.1.

Side by side

GPT-4.5GPT-5.1
ProviderOpenAIOpenAI
Noometry Index37.249.0
Released2025-02-272025-11-13
WeightsProprietaryProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$1.25
Output $ / M tokens—$10
Results tracked4263

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GPT-5.1 leads

GPT-4.5: 42.2 (#109), GPT-5.1: 46.4 (#66)

BenchmarkGPT-4.5GPT-5.1
WeirdML39.4%60.8%
LiveBench Coding75.2%72.5%
LMArena Coding13961454
SWE-bench Verified—68%
SWE-bench Verified (bash only)—66%
Aider Polyglot44.9%—
LMArena WebDev—1395
SciCode—43.3%
GSO—13.7%
ALE-Bench—1,192

Agentic & Tool Use GPT-5.1 leads

GPT-4.5: 27.9 (#97), GPT-5.1: 32.7 (#60)

BenchmarkGPT-4.5GPT-5.1
Terminal-Bench—47.6%
Cybench17.5%—
DeepResearch Bench—42.8%
LMArena Search—1199
Vending-Bench 2—1,473

Reasoning GPT-5.1 leads

GPT-4.5: 13.9 (#330), GPT-5.1: 39.8 (#58)

BenchmarkGPT-4.5GPT-5.1
ARC-AGI-20.8%17.6%
SimpleBench34.5%53.2%
ARC-AGI-110.3%72.8%
EnigmaEval3.2%11.2%
LiveBench Reasoning71.1%95.8%
LMArena Hard Prompts14031457
LiveBench Data Analysis64.3%72.1%
Epoch Capabilities Index136.74149.64
ForecastBench61.758.1
LiveBench69%78.8%
CritPt—4.9%
Chess Puzzles—32%
Mystery Game Puzzles—19%
DTBench—90.1%
LMCA—43.9%

Math GPT-5.1 leads

GPT-4.5: 32.6 (#211), GPT-5.1: 52.2 (#51)

BenchmarkGPT-4.5GPT-5.1
OTIS Mock AIME 2024-202537.8%88.6%
LiveBench Math69.3%94.5%
LMArena Math14121447
Omni-MATH—46.4%
MATH Level 578.6%—
FrontierMath (Feb 2025 set)—31%
FrontierMath Tier 4 (v1)—12.5%

Knowledge GPT-5.1 leads

GPT-4.5: 32.5 (#211), GPT-5.1: 50.6 (#71)

BenchmarkGPT-4.5GPT-5.1
GPQA Diamond68.7%87.6%
Humanity's Last Exam5.4%23.7%
LMArena Expert13941470
SimpleQA Verified—48%
MMLU-Pro—57.9%
Confabulations13.6%—
Vectara Hallucination Rate—10.9%
GPQA (HELM)—44.2%

Multimodal GPT-5.1 leads

GPT-4.5: 37.6 (#71), GPT-5.1: 44.8 (#19)

BenchmarkGPT-4.5GPT-5.1
LMArena Vision11951250
VPCT45%58.7%
LMArena Document—1403

Multilingual GPT-5.1 leads

GPT-4.5: 52.5 (#83), GPT-5.1: 53.8 (#56)

BenchmarkGPT-4.5GPT-5.1
LMArena Non-English14131431
LMArena Chinese14211495
LMArena French14181450
LMArena German14571438
LMArena Japanese14161453
LMArena Korean13921401
LMArena Russian14191435
LMArena Spanish—1433

Instruction Following GPT-5.1 leads

GPT-4.5: 72.6 (#134), GPT-5.1: 83.9 (#1)

BenchmarkGPT-4.5GPT-5.1
LiveBench Instruction Following72.3%93.3%
LMArena Instruction Following14041443
IFEval—93.5%

Long Context GPT-5.1 leads

GPT-4.5: 40.4 (#155), GPT-5.1: 47.6 (#14)

BenchmarkGPT-4.5GPT-5.1
LMArena Longer Query14061447
Fiction.LiveBench63.9%—
CL-bench—23.7%
CL-bench Life—17.3%

Writing & Preference GPT-5.1 leads

GPT-4.5: 56.9 (#134), GPT-5.1: 64.5 (#55)

BenchmarkGPT-4.5GPT-5.1
LMArena Text14171443
LMArena Creative Writing13941427
LMArena Multi-Turn14441450
LiveBench Language61.5%80.2%
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
WildBench—86.3%

Frequently asked questions

Is GPT-4.5 better than GPT-5.1?

GPT-5.1 is the stronger model overall, scoring 49.0 to 37.2 on the Noometry Index.

Is GPT-4.5 or GPT-5.1 better for coding?

GPT-5.1 scores higher on coding benchmarks: 46.4 versus 42.2 in the Noometry coding category.

How many benchmarks do GPT-4.5 and GPT-5.1 share?

35 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and GPT-5.1 has 63.

Related comparisons

Go deeper