Noometry

Model comparison

Grok-3 mini vs Grok 4.5

Grok 4.5 is the stronger model overall, scoring 55.0 to 41.2 on the Noometry Index.

Last verified . 24 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Grok 4.5 xAI

55.0

Rank #25 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Grok 4.5 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.5 leads 56.1 to 13.6.
  • The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 87.2% for Grok 4.5.

Side by side

Grok-3 miniGrok 4.5
ProviderxAIxAI
Noometry Index41.255.0
Released2025-04-092026-07-08
WeightsProprietaryProprietary
Context window—500K
Max output—500K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3552

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

Category by category

Coding Grok 4.5 leads

Grok-3 mini: 40.8 (#131), Grok 4.5: 52.2 (#35)

BenchmarkGrok-3 miniGrok 4.5
WeirdML42.6%46.4%
LMArena Coding13791474
DeepSWE—53.8%
FrontierCode—42.4%
Aider Polyglot49.3%—
LMArena WebDev—1553
SciCode—54.1%
ALE-Bench—1,309

Agentic & Tool Use Not comparable

Grok-3 mini: —, Grok 4.5: 44.4 (#17)

BenchmarkGrok-3 miniGrok 4.5
APEX-Agents—56.2%
τ²-bench Banking—47.9%
PostTrainBench—23.4%
GBAEval—65.4%
GDP.pdf—14%
LMArena Search—1213
Vending-Bench 2—3,887

Reasoning Grok 4.5 leads

Grok-3 mini: 13.6 (#334), Grok 4.5: 56.1 (#25)

BenchmarkGrok-3 miniGrok 4.5
ARC-AGI-20.4%52.6%
Kagi LLM Benchmark61.3%83.5%
ARC-AGI-116.5%87.2%
LMArena Hard Prompts13751462
Epoch Capabilities Index140.35153.92
SimpleBench—70%
NYT Connections (extended)—79.9%
CritPt—15.4%
Chess Puzzles—36%
DTBench—96.5%
LMCA—45.2%
Surface Evolver Bench—74.4%

Math Grok 4.5 leads

Grok-3 mini: 42.1 (#85), Grok 4.5: 60.9 (#35)

BenchmarkGrok-3 miniGrok 4.5
OTIS Mock AIME 2024-202577.8%97.8%
LMArena Math13861459
FrontierMath (Tiers 1-3)—57.2%
FrontierMath Tier 4—24.4%
ProofBench—31%
Omni-MATH31.8%—
MATH Level 590.9%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok 4.5 leads

Grok-3 mini: 46.4 (#81), Grok 4.5: 62.3 (#24)

BenchmarkGrok-3 miniGrok 4.5
GPQA Diamond76.3%93.4%
LMArena Expert13951466
SimpleQA Verified—48.3%
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—

Multimodal Not comparable

Grok-3 mini: —, Grok 4.5: 37.6 (#72)

BenchmarkGrok-3 miniGrok 4.5
LMArena Vision—1288
Blueprint-Bench 2—27.3%
Furniture Assembly—22.5%
LMArena Document—1452

Multilingual Grok 4.5 leads

Grok-3 mini: 48.1 (#145), Grok 4.5: 54.4 (#42)

BenchmarkGrok-3 miniGrok 4.5
LMArena Non-English13521440
LMArena Chinese13871496
LMArena French13571456
LMArena German13491446
LMArena Japanese13421428
LMArena Korean13351404
LMArena Russian13531448
LMArena Spanish13811450

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Grok 4.5: 76.0 (#48)

BenchmarkGrok-3 miniGrok 4.5
LMArena Instruction Following13571446
IFEval95.1%—

Long Context Grok 4.5 leads

Grok-3 mini: 41.0 (#147), Grok 4.5: 44.8 (#56)

BenchmarkGrok-3 miniGrok 4.5
LMArena Longer Query13721463
Fiction.LiveBench66.7%—

Writing & Preference Grok 4.5 leads

Grok-3 mini: 52.5 (#169), Grok 4.5: 65.8 (#42)

BenchmarkGrok-3 miniGrok 4.5
LMArena Text13701448
LMArena Creative Writing13421442
LMArena Multi-Turn13551456
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing—1579
WildBench65.1%—

Frequently asked questions

Is Grok-3 mini better than Grok 4.5?

Grok 4.5 is the stronger model overall, scoring 55.0 to 41.2 on the Noometry Index.

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

Grok 4.5 scores higher on coding benchmarks: 52.2 versus 40.8 in the Noometry coding category.

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

24 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Grok 4.5 has 52.

Related comparisons

Go deeper