Noometry

Model comparison

GPT-4.5 vs Grok-2 (Dec 2024)

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.7 on the Noometry Index.

Last verified . 31 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Summary

  • They share 31 benchmarks with published results for both. GPT-4.5 scores higher in 7 categories and Grok-2 (Dec 2024) in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-4.5 leads 32.6 to 20.8.
  • The biggest single-benchmark swing is LiveBench Coding: 75.2% for GPT-4.5 and 46.4% for Grok-2 (Dec 2024).

Side by side

GPT-4.5Grok-2 (Dec 2024)
ProviderOpenAIxAI
Noometry Index37.233.7
Released2025-02-272024-08-13
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4234

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), Grok-2 (Dec 2024): 33.3 (#258)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
WeirdML39.4%22.2%
LiveBench Coding75.2%46.4%
LMArena Coding13961287
Aider Polyglot44.9%—

Agentic & Tool Use Not comparable

GPT-4.5: 27.9 (#97), Grok-2 (Dec 2024): —

BenchmarkGPT-4.5Grok-2 (Dec 2024)
Cybench17.5%—

Reasoning Grok-2 (Dec 2024) leads

GPT-4.5: 13.9 (#330), Grok-2 (Dec 2024): 16.9 (#299)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
SimpleBench34.5%22.7%
LiveBench Reasoning71.1%54.8%
LMArena Hard Prompts14031272
LiveBench Data Analysis64.3%54.5%
Epoch Capabilities Index136.74130.48
LiveBench69%54.3%
ARC-AGI-20.8%—
ARC-AGI-110.3%—
EnigmaEval3.2%—
DTBench—65.2%
ForecastBench61.7—

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), Grok-2 (Dec 2024): 20.8 (#284)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
OTIS Mock AIME 2024-202537.8%11.5%
LiveBench Math69.3%54.9%
LMArena Math14121283
MATH Level 578.6%63.5%
FrontierMath (Feb 2025 set)—0.7%

Knowledge GPT-4.5 leads

GPT-4.5: 32.5 (#211), Grok-2 (Dec 2024): 29.8 (#233)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
GPQA Diamond68.7%53.8%
Confabulations13.6%20.1%
LMArena Expert13941254
Humanity's Last Exam5.4%—

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Grok-2 (Dec 2024): —

BenchmarkGPT-4.5Grok-2 (Dec 2024)
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), Grok-2 (Dec 2024): 43.1 (#188)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
LMArena Non-English14131282
LMArena Chinese14211289
LMArena French14181318
LMArena German14571287
LMArena Japanese14161244
LMArena Korean13921237
LMArena Russian14191286
LMArena Spanish—1281

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), Grok-2 (Dec 2024): 66.9 (#202)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
LiveBench Instruction Following72.3%69.6%
LMArena Instruction Following14041270

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), Grok-2 (Dec 2024): 38.8 (#190)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
LMArena Longer Query14061276
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), Grok-2 (Dec 2024): 48.6 (#198)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
LMArena Text14171305
LMArena Creative Writing13941284
Short-Story Creative Writing75.6%63.6%
LMArena Multi-Turn14441290
LiveBench Language61.5%45.6%
EQ-Bench Creative Writing1258—

Frequently asked questions

Is GPT-4.5 better than Grok-2 (Dec 2024)?

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.7 on the Noometry Index.

Is GPT-4.5 or Grok-2 (Dec 2024) better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 33.3 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Grok-2 (Dec 2024) share?

31 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Grok-2 (Dec 2024) has 34.

Related comparisons

Go deeper