Noometry

Model comparison

GPT-4.5 vs Grok-3 mini

Grok-3 mini is the stronger model overall, scoring 41.0 to 36.9 on the Noometry Index.

Last verified . 27 shared benchmarks.

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

Grok-3 mini xAI

41.0

Rank #130 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-4.5 scores higher in 4 categories and Grok-3 mini in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-3 mini leads 46.3 to 32.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 77.8% for Grok-3 mini.

Side by side

GPT-4.5Grok-3 mini
ProviderOpenAIxAI
Noometry Index36.941.0
Released2025-02-272025-04-09
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4235

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-3 mini: 40.4 (#126)

BenchmarkGPT-4.5Grok-3 mini
Aider Polyglot44.9%49.3%
WeirdML39.4%42.6%
LMArena Coding13971380
LiveBench Coding75.2%—

Agentic & Tool Use Not comparable

GPT-4.5: 27.6 (#92), Grok-3 mini: —

BenchmarkGPT-4.5Grok-3 mini
Cybench17.5%—

Reasoning Too close to call

GPT-4.5: 14.1 (#320), Grok-3 mini: 13.8 (#323)

BenchmarkGPT-4.5Grok-3 mini
ARC-AGI-20.8%0.4%
ARC-AGI-110.3%16.5%
LMArena Hard Prompts14041374
Epoch Capabilities Index136.74140.35
SimpleBench34.5%—
Kagi LLM Benchmark—61.3%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LiveBench Data Analysis64.3%—
ForecastBench61.7—
LiveBench69%—

Math Grok-3 mini leads

GPT-4.5: 31.0 (#200), Grok-3 mini: 40.3 (#78)

BenchmarkGPT-4.5Grok-3 mini
OTIS Mock AIME 2024-202537.8%77.8%
LMArena Math14121386
MATH Level 578.6%90.9%
Omni-MATH—31.8%
LiveBench Math69.3%—
FrontierMath (Feb 2025 set)—5.9%

Knowledge Grok-3 mini leads

GPT-4.5: 32.4 (#205), Grok-3 mini: 46.3 (#75)

BenchmarkGPT-4.5Grok-3 mini
GPQA Diamond68.7%76.3%
Confabulations13.6%10.8%
LMArena Expert13941395
Humanity's Last Exam5.4%—
MMLU-Pro—79.9%
GPQA (HELM)—67.5%

Multimodal Not comparable

GPT-4.5: 37.0 (#68), Grok-3 mini: —

BenchmarkGPT-4.5Grok-3 mini
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.7 (#78), Grok-3 mini: 48.3 (#141)

BenchmarkGPT-4.5Grok-3 mini
LMArena Non-English14131352
LMArena Chinese14211387
LMArena French14171357
LMArena German14571350
LMArena Japanese14161343
LMArena Korean13921336
LMArena Russian14191352
LMArena Spanish—1379

Instruction Following Grok-3 mini leads

GPT-4.5: 72.8 (#129), Grok-3 mini: 78.7 (#8)

BenchmarkGPT-4.5Grok-3 mini
LMArena Instruction Following14041356
LiveBench Instruction Following72.3%—
IFEval—95.1%

Long Context Too close to call

GPT-4.5: 40.4 (#150), Grok-3 mini: 41.0 (#142)

BenchmarkGPT-4.5Grok-3 mini
Fiction.LiveBench63.9%66.7%
LMArena Longer Query14061372

Writing & Preference GPT-4.5 leads

GPT-4.5: 57.1 (#129), Grok-3 mini: 52.7 (#163)

BenchmarkGPT-4.5Grok-3 mini
LMArena Text14171370
LMArena Creative Writing13941342
Short-Story Creative Writing75.6%73.5%
LMArena Multi-Turn14441355
EQ-Bench Creative Writing1258—
WildBench—65.1%
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.0 to 36.9 on the Noometry Index.

Is GPT-4.5 or Grok-3 mini better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 40.4 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Grok-3 mini share?

27 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper