Noometry

Model comparison

GPT-4.5 vs Grok-2 (Dec 2024)

GPT-4.5 is the stronger model overall, scoring 36.9 to 33.4 on the Noometry Index.

Last verified . 31 shared benchmarks.

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

Grok-2 (Dec 2024) xAI

33.4

Rank #233 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 31.0 to 19.6.
  • 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 Index36.933.4
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: 41.8 (#102), Grok-2 (Dec 2024): 32.9 (#254)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
WeirdML39.4%22.2%
LiveBench Coding75.2%46.4%
LMArena Coding13971288
Aider Polyglot44.9%—

Agentic & Tool Use Not comparable

GPT-4.5: 27.6 (#92), Grok-2 (Dec 2024): —

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

Reasoning Grok-2 (Dec 2024) leads

GPT-4.5: 14.1 (#320), Grok-2 (Dec 2024): 16.4 (#294)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
SimpleBench34.5%22.7%
LiveBench Reasoning71.1%54.8%
LMArena Hard Prompts14041272
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: 31.0 (#200), Grok-2 (Dec 2024): 19.6 (#278)

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: 32.4 (#205), Grok-2 (Dec 2024): 29.8 (#225)

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: 37.0 (#68), Grok-2 (Dec 2024): —

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

Multilingual GPT-4.5 leads

GPT-4.5: 52.7 (#78), Grok-2 (Dec 2024): 43.3 (#183)

BenchmarkGPT-4.5Grok-2 (Dec 2024)
LMArena Non-English14131282
LMArena Chinese14211289
LMArena French14171317
LMArena German14571287
LMArena Japanese14161244
LMArena Korean13921237
LMArena Russian14191286
LMArena Spanish—1281

Instruction Following GPT-4.5 leads

GPT-4.5: 72.8 (#129), Grok-2 (Dec 2024): 67.1 (#197)

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 (#150), Grok-2 (Dec 2024): 38.7 (#186)

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

Writing & Preference GPT-4.5 leads

GPT-4.5: 57.1 (#129), Grok-2 (Dec 2024): 48.8 (#192)

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 36.9 to 33.4 on the Noometry Index.

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

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 32.9 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