Noometry

Model comparison

Grok-2 (Dec 2024) vs Grok 4.3

Grok 4.3 is the stronger model overall, scoring 43.8 to 33.7 on the Noometry Index.

Last verified . 22 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Grok 4.3 xAI

43.8

Rank #86 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Grok 4.3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.3 leads 46.0 to 20.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 93.3% for Grok 4.3.

Side by side

Grok-2 (Dec 2024)Grok 4.3
ProviderxAIxAI
Noometry Index33.743.8
Released2024-08-132026-04-17
WeightsProprietaryProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked3440

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

Category by category

Coding Grok 4.3 leads

Grok-2 (Dec 2024): 33.3 (#258), Grok 4.3: 41.6 (#121)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
WeirdML22.2%49.9%
LMArena Coding12871415
LMArena WebDev—1357
SciCode—47.3%
LiveBench Coding46.4%—
ALE-Bench—944.17

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Grok 4.3: 27.7 (#99)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
GDP.pdf—8%
LMArena Search—1165
Vending-Bench 2—35.26

Reasoning Grok 4.3 leads

Grok-2 (Dec 2024): 16.9 (#299), Grok 4.3: 35.9 (#68)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
LMArena Hard Prompts12721396
DTBench65.2%90.7%
Epoch Capabilities Index130.48149.16
SimpleBench22.7%—
NYT Connections (extended)—55.2%
CritPt—8%
Chess Puzzles—25%
LiveBench Reasoning54.8%—
LiveBench Data Analysis54.5%—
LMCA—38.3%
ForecastBench—60.3
LiveBench54.3%—

Math Grok 4.3 leads

Grok-2 (Dec 2024): 20.8 (#284), Grok 4.3: 46.0 (#74)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
OTIS Mock AIME 2024-202511.5%93.3%
LMArena Math12831388
FrontierMath (Tiers 1-3)—42.8%
FrontierMath Tier 4—14.6%
ProofBench—11%
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Grok 4.3 leads

Grok-2 (Dec 2024): 29.8 (#233), Grok 4.3: 52.5 (#62)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
GPQA Diamond53.8%88.8%
LMArena Expert12541385
SimpleQA Verified—33.2%
Confabulations20.1%—

Multimodal Not comparable

Grok-2 (Dec 2024): —, Grok 4.3: 31.6 (#104)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
LMArena Vision—1229
Blueprint-Bench 2—0%

Multilingual Grok 4.3 leads

Grok-2 (Dec 2024): 43.1 (#188), Grok 4.3: 50.5 (#120)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
LMArena Non-English12821385
LMArena Chinese12891422
LMArena French13181412
LMArena German12871395
LMArena Japanese12441379
LMArena Korean12371356
LMArena Russian12861399
LMArena Spanish12811398

Instruction Following Grok 4.3 leads

Grok-2 (Dec 2024): 66.9 (#202), Grok 4.3: 72.1 (#140)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
LMArena Instruction Following12701366
LiveBench Instruction Following69.6%—

Long Context Grok 4.3 leads

Grok-2 (Dec 2024): 38.8 (#190), Grok 4.3: 42.5 (#123)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
LMArena Longer Query12761393

Writing & Preference Grok 4.3 leads

Grok-2 (Dec 2024): 48.6 (#198), Grok 4.3: 58.5 (#118)

BenchmarkGrok-2 (Dec 2024)Grok 4.3
LMArena Text13051397
LMArena Creative Writing12841380
LMArena Multi-Turn12901406
Short-Story Creative Writing63.6%—
EQ-Bench 4—1075
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Grok 4.3?

Grok 4.3 is the stronger model overall, scoring 43.8 to 33.7 on the Noometry Index.

Is Grok-2 (Dec 2024) or Grok 4.3 better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.6 versus 33.3 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Grok 4.3 share?

22 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Grok 4.3 has 40.

Related comparisons

Go deeper