Noometry

Model comparison

Grok 3 vs Grok 4.3

Grok 4.3 is the stronger model overall, scoring 43.8 to 39.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok 3 xAI

39.9

Rank #157 Confirmed

Grok 4.3 xAI

43.8

Rank #86 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok 3 scores higher in 4 categories and Grok 4.3 in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.3 leads 35.9 to 13.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 93.3% for Grok 4.3.

Side by side

Grok 3Grok 4.3
ProviderxAIxAI
Noometry Index39.943.8
Released2025-04-092026-04-17
WeightsProprietaryProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked4040

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

Category by category

Coding Too close to call

Grok 3: 41.9 (#115), Grok 4.3: 41.6 (#121)

BenchmarkGrok 3Grok 4.3
WeirdML37.2%49.9%
LMArena Coding14321415
Aider Polyglot53.3%—
LMArena WebDev—1357
SciCode—47.3%
ALE-Bench—944.17

Agentic & Tool Use Grok 3 leads

Grok 3: 30.5 (#76), Grok 4.3: 27.7 (#99)

BenchmarkGrok 3Grok 4.3
BALROG29.5%—
GDP.pdf—8%
LMArena Search—1165
Vending-Bench 2—35.26

Reasoning Grok 4.3 leads

Grok 3: 13.7 (#333), Grok 4.3: 35.9 (#68)

BenchmarkGrok 3Grok 4.3
LMArena Hard Prompts14341396
Epoch Capabilities Index138.33149.16
ARC-AGI-20%—
SimpleBench36.1%—
Kagi LLM Benchmark61.3%—
NYT Connections (extended)—55.2%
ARC-AGI-15.5%—
CritPt—8%
Chess Puzzles—25%
DTBench—90.7%
LMCA—38.3%
ForecastBench—60.3

Math Grok 4.3 leads

Grok 3: 38.0 (#145), Grok 4.3: 46.0 (#74)

BenchmarkGrok 3Grok 4.3
OTIS Mock AIME 2024-202555.6%93.3%
LMArena Math13911388
FrontierMath (Tiers 1-3)—42.8%
FrontierMath Tier 4—14.6%
ProofBench—11%
Omni-MATH46.4%—
MATH Level 588.7%—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)0%—

Knowledge Grok 4.3 leads

Grok 3: 46.2 (#82), Grok 4.3: 52.5 (#62)

BenchmarkGrok 3Grok 4.3
GPQA Diamond75.8%88.8%
LMArena Expert14211385
SimpleQA Verified—33.2%
MMLU-Pro78.8%—
Confabulations14.2%—
Vectara Hallucination Rate5.8%—
GPQA (HELM)65%—

Multimodal Not comparable

Grok 3: —, Grok 4.3: 31.6 (#104)

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

Multilingual Grok 3 leads

Grok 3: 52.3 (#87), Grok 4.3: 50.5 (#120)

BenchmarkGrok 3Grok 4.3
LMArena Non-English14101385
LMArena Chinese14481422
LMArena French14601412
LMArena German14311395
LMArena Japanese13871379
LMArena Korean13731356
LMArena Russian14161399
LMArena Spanish14171398

Instruction Following Grok 3 leads

Grok 3: 75.0 (#73), Grok 4.3: 72.1 (#140)

BenchmarkGrok 3Grok 4.3
LMArena Instruction Following14091366
IFEval88.4%—

Long Context Grok 4.3 leads

Grok 3: 38.7 (#192), Grok 4.3: 42.5 (#123)

BenchmarkGrok 3Grok 4.3
LMArena Longer Query14391393
Fiction.LiveBench58.3%—

Writing & Preference Grok 4.3 leads

Grok 3: 55.8 (#141), Grok 4.3: 58.5 (#118)

BenchmarkGrok 3Grok 4.3
LMArena Text14261397
LMArena Creative Writing14141380
LMArena Multi-Turn14251406
Short-Story Creative Writing76.4%—
EQ-Bench Creative Writing1186—
WildBench84.9%—
EQ-Bench 4—1075

Frequently asked questions

Is Grok 3 better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.8 to 39.9 on the Noometry Index.

Is Grok 3 or Grok 4.3 better for coding?

They score almost the same on coding (41.9 vs 41.6); test both on your own repository before choosing.

How many benchmarks do Grok 3 and Grok 4.3 share?

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

Related comparisons

Go deeper