Noometry

Model comparison

Grok 4 vs Grok 4.3

Grok 4 is the stronger model overall, scoring 47.8 to 43.6 on the Noometry Index.

Last verified . 25 shared benchmarks.

Grok 4 xAI

47.8

Rank #49 Confirmed

Grok 4.3 xAI

43.6

Rank #80 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Grok 4 scores higher in 10 categories and Grok 4.3 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 42.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84% for Grok 4 and 93.3% for Grok 4.3.

Side by side

Grok 4Grok 4.3
ProviderxAIxAI
Noometry Index47.843.6
Released2025-07-092026-04-17
WeightsProprietaryProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked4840

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

Category by category

Coding Grok 4 leads

Grok 4: 49.9 (#44), Grok 4.3: 41.3 (#117)

BenchmarkGrok 4Grok 4.3
WeirdML45.7%49.9%
LMArena Coding14081415
Aider Polyglot79.6%—
LMArena WebDev—1357
SciCode—47.3%
ALE-Bench—944.17

Agentic & Tool Use Grok 4 leads

Grok 4: 32.1 (#62), Grok 4.3: 27.6 (#93)

BenchmarkGrok 4Grok 4.3
LMArena Search11421165
Terminal-Bench27.2%—
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
GDP.pdf—8%
METR Time Horizons66.6%—
Vending-Bench 2—35.26

Reasoning Grok 4 leads

Grok 4: 36.9 (#59), Grok 4.3: 34.9 (#60)

BenchmarkGrok 4Grok 4.3
Chess Puzzles28%25%
LMArena Hard Prompts14091397
Epoch Capabilities Index146.46149.13
ForecastBench60.960.3
ARC-AGI-216%—
SimpleBench60.5%—
Kagi LLM Benchmark73.6%—
NYT Connections (extended)—55.2%
ARC-AGI-166.7%—
CritPt—8%
DTBench—90.7%
LMCA—38.3%

Math Too close to call

Grok 4: 46.5 (#58), Grok 4.3: 45.8 (#60)

BenchmarkGrok 4Grok 4.3
OTIS Mock AIME 2024-202584%93.3%
LMArena Math14221388
FrontierMath (Tiers 1-3)—42.8%
FrontierMath Tier 4—14.6%
ProofBench—11%
Omni-MATH60.3%—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4 leads

Grok 4: 53.7 (#50), Grok 4.3: 52.5 (#57)

BenchmarkGrok 4Grok 4.3
GPQA Diamond87%88.8%
LMArena Expert14171385
SimpleQA Verified—33.2%
MMLU-Pro85.1%—
Confabulations12.4%—
GPQA (HELM)72.7%—

Multimodal Grok 4 leads

Grok 4: 33.1 (#89), Grok 4.3: 31.6 (#96)

BenchmarkGrok 4Grok 4.3
LMArena Vision12111231
GeoBench45%—
Blueprint-Bench 2—0%

Multilingual Grok 4 leads

Grok 4: 52.0 (#98), Grok 4.3: 50.7 (#114)

BenchmarkGrok 4Grok 4.3
LMArena Non-English14031385
LMArena Chinese14281423
LMArena French14181412
LMArena German14291395
LMArena Japanese13961379
LMArena Korean13761357
LMArena Russian14091399
LMArena Spanish14191402

Instruction Following Grok 4 leads

Grok 4: 79.4 (#4), Grok 4.3: 72.3 (#135)

BenchmarkGrok 4Grok 4.3
LMArena Instruction Following13871366
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Grok 4.3: 42.5 (#118)

BenchmarkGrok 4Grok 4.3
LMArena Longer Query14091393
Fiction.LiveBench94.4%—

Writing & Preference Too close to call

Grok 4: 58.7 (#111), Grok 4.3: 58.6 (#112)

BenchmarkGrok 4Grok 4.3
LMArena Text14121397
LMArena Creative Writing13971380
LMArena Multi-Turn14161406
Short-Story Creative Writing76.9%—
WildBench79.7%—
EQ-Bench 4—1075

Frequently asked questions

Is Grok 4 better than Grok 4.3?

Grok 4 is the stronger model overall, scoring 47.8 to 43.6 on the Noometry Index.

Is Grok 4 or Grok 4.3 better for coding?

Grok 4 scores higher on coding benchmarks: 49.9 versus 41.3 in the Noometry coding category.

How many benchmarks do Grok 4 and Grok 4.3 share?

25 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Grok 4.3 has 40.

Related comparisons

Go deeper