Noometry

Model comparison

GPT-4.5 vs GPT-4 Turbo

GPT-4.5 is the stronger model overall, scoring 37.2 to 30.5 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4.5 scores higher in 8 categories and GPT-4 Turbo in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-4.5 leads 32.6 to 9.0.
  • The biggest single-benchmark swing is MATH Level 5: 78.6% for GPT-4.5 and 46.7% for GPT-4 Turbo.

Side by side

GPT-4.5GPT-4 Turbo
ProviderOpenAIOpenAI
Noometry Index37.230.5
Released2025-02-272023-11-06
WeightsProprietaryProprietary
Context window—128K
Max output—4K
Input $ / M tokens—$10
Output $ / M tokens—$30
Results tracked4236

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), GPT-4 Turbo: 33.8 (#249)

BenchmarkGPT-4.5GPT-4 Turbo
WeirdML39.4%18%
LMArena Coding13961268
Aider Polyglot44.9%—
BigCodeBench Instruct—48.2%
LiveBench Coding75.2%—
BigCodeBench Complete—58.2%
HumanEval+—86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

GPT-4.5: 27.9 (#97), GPT-4 Turbo: —

BenchmarkGPT-4.5GPT-4 Turbo
Cybench17.5%—
METR Time Horizons—36.7%

Reasoning GPT-4 Turbo leads

GPT-4.5: 13.9 (#330), GPT-4 Turbo: 15.3 (#317)

BenchmarkGPT-4.5GPT-4 Turbo
SimpleBench34.5%25.1%
LMArena Hard Prompts14031251
Epoch Capabilities Index136.74127.25
ForecastBench61.759.4
ARC-AGI-20.8%—
ARC-AGI-110.3%—
Chess Puzzles—6%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
DTBench—61.6%
LiveBench Data Analysis64.3%—
LMCA—9.8%
LiveBench69%—

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), GPT-4 Turbo: 9.0 (#322)

BenchmarkGPT-4.5GPT-4 Turbo
OTIS Mock AIME 2024-202537.8%6.7%
LMArena Math14121272
MATH Level 578.6%46.7%
FrontierMath (Tiers 1-3)—0.7%
LiveBench Math69.3%—

Knowledge GPT-4.5 leads

GPT-4.5: 32.5 (#211), GPT-4 Turbo: 24.3 (#268)

BenchmarkGPT-4.5GPT-4 Turbo
GPQA Diamond68.7%46.6%
Confabulations13.6%28.4%
LMArena Expert13941223
Humanity's Last Exam5.4%—
MMLU—81.3%

Multimodal GPT-4.5 leads

GPT-4.5: 37.6 (#71), GPT-4 Turbo: 30.6 (#110)

BenchmarkGPT-4.5GPT-4 Turbo
LMArena Vision11951090
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), GPT-4 Turbo: 40.5 (#216)

BenchmarkGPT-4.5GPT-4 Turbo
LMArena Non-English14131245
LMArena Chinese14211242
LMArena French14181276
LMArena German14571259
LMArena Japanese14161194
LMArena Korean13921187
LMArena Russian14191259
LMArena Spanish—1260

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), GPT-4 Turbo: 65.8 (#216)

BenchmarkGPT-4.5GPT-4 Turbo
LMArena Instruction Following14041249
LiveBench Instruction Following72.3%—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), GPT-4 Turbo: 38.0 (#206)

BenchmarkGPT-4.5GPT-4 Turbo
LMArena Longer Query14061254
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), GPT-4 Turbo: 47.7 (#206)

BenchmarkGPT-4.5GPT-4 Turbo
LMArena Text14171272
LMArena Creative Writing13941269
LMArena Multi-Turn14441267
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than GPT-4 Turbo?

GPT-4.5 is the stronger model overall, scoring 37.2 to 30.5 on the Noometry Index.

Is GPT-4.5 or GPT-4 Turbo better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 33.8 in the Noometry coding category.

How many benchmarks do GPT-4.5 and GPT-4 Turbo share?

25 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and GPT-4 Turbo has 36.

Related comparisons

Go deeper