Noometry

Model comparison

Grok-3 mini vs Grok 4.3

Grok 4.3 is the stronger model overall, scoring 43.8 to 41.2 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Grok 4.3 xAI

43.8

Rank #86 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Grok 4.3 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.3 leads 35.9 to 13.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 93.3% for Grok 4.3.

Side by side

Grok-3 miniGrok 4.3
ProviderxAIxAI
Noometry Index41.243.8
Released2025-04-092026-04-17
WeightsProprietaryProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked3540

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

Category by category

Coding Too close to call

Grok-3 mini: 40.8 (#131), Grok 4.3: 41.6 (#121)

BenchmarkGrok-3 miniGrok 4.3
WeirdML42.6%49.9%
LMArena Coding13791415
Aider Polyglot49.3%—
LMArena WebDev—1357
SciCode—47.3%
ALE-Bench—944.17

Agentic & Tool Use Not comparable

Grok-3 mini: —, Grok 4.3: 27.7 (#99)

BenchmarkGrok-3 miniGrok 4.3
GDP.pdf—8%
LMArena Search—1165
Vending-Bench 2—35.26

Reasoning Grok 4.3 leads

Grok-3 mini: 13.6 (#334), Grok 4.3: 35.9 (#68)

BenchmarkGrok-3 miniGrok 4.3
LMArena Hard Prompts13751396
Epoch Capabilities Index140.35149.16
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
NYT Connections (extended)—55.2%
ARC-AGI-116.5%—
CritPt—8%
Chess Puzzles—25%
DTBench—90.7%
LMCA—38.3%
ForecastBench—60.3

Math Grok 4.3 leads

Grok-3 mini: 42.1 (#85), Grok 4.3: 46.0 (#74)

BenchmarkGrok-3 miniGrok 4.3
OTIS Mock AIME 2024-202577.8%93.3%
LMArena Math13861388
FrontierMath (Tiers 1-3)—42.8%
FrontierMath Tier 4—14.6%
ProofBench—11%
Omni-MATH31.8%—
MATH Level 590.9%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok 4.3 leads

Grok-3 mini: 46.4 (#81), Grok 4.3: 52.5 (#62)

BenchmarkGrok-3 miniGrok 4.3
GPQA Diamond76.3%88.8%
LMArena Expert13951385
SimpleQA Verified—33.2%
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—

Multimodal Not comparable

Grok-3 mini: —, Grok 4.3: 31.6 (#104)

BenchmarkGrok-3 miniGrok 4.3
LMArena Vision—1229
Blueprint-Bench 2—0%

Multilingual Grok 4.3 leads

Grok-3 mini: 48.1 (#145), Grok 4.3: 50.5 (#120)

BenchmarkGrok-3 miniGrok 4.3
LMArena Non-English13521385
LMArena Chinese13871422
LMArena French13571412
LMArena German13491395
LMArena Japanese13421379
LMArena Korean13351356
LMArena Russian13531399
LMArena Spanish13811398

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Grok 4.3: 72.1 (#140)

BenchmarkGrok-3 miniGrok 4.3
LMArena Instruction Following13571366
IFEval95.1%—

Long Context Grok 4.3 leads

Grok-3 mini: 41.0 (#147), Grok 4.3: 42.5 (#123)

BenchmarkGrok-3 miniGrok 4.3
LMArena Longer Query13721393
Fiction.LiveBench66.7%—

Writing & Preference Grok 4.3 leads

Grok-3 mini: 52.5 (#169), Grok 4.3: 58.5 (#118)

BenchmarkGrok-3 miniGrok 4.3
LMArena Text13701397
LMArena Creative Writing13421380
LMArena Multi-Turn13551406
Short-Story Creative Writing73.5%—
WildBench65.1%—
EQ-Bench 4—1075

Frequently asked questions

Is Grok-3 mini better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.8 to 41.2 on the Noometry Index.

Is Grok-3 mini or Grok 4.3 better for coding?

They score almost the same on coding (40.8 vs 41.6); test both on your own repository before choosing.

How many benchmarks do Grok-3 mini and Grok 4.3 share?

21 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Grok 4.3 has 40.

Related comparisons

Go deeper