Noometry

Model comparison

Grok 3 vs Grok 4.20 Multi-Agent

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 39.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Grok 3 xAI

39.9

Rank #157 Confirmed

Grok 4.20 Multi-Agent xAI

46.2

Rank #65 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Grok 3 scores higher in 2 categories and Grok 4.20 Multi-Agent in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 13.7.

Side by side

Grok 3Grok 4.20 Multi-Agent
ProviderxAIxAI
Noometry Index39.946.2
Released2025-04-092026-03-09
WeightsProprietaryProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked4020

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

Category by category

Coding Grok 4.20 Multi-Agent leads

Grok 3: 41.9 (#115), Grok 4.20 Multi-Agent: 43.0 (#92)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Coding14321457
Aider Polyglot53.3%—
WeirdML37.2%—

Agentic & Tool Use Not comparable

Grok 3: 30.5 (#76), Grok 4.20 Multi-Agent: —

BenchmarkGrok 3Grok 4.20 Multi-Agent
BALROG29.5%—
LMArena Search—1204

Reasoning Grok 4.20 Multi-Agent leads

Grok 3: 13.7 (#333), Grok 4.20 Multi-Agent: 43.9 (#48)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Hard Prompts14341448
ARC-AGI-20%—
SimpleBench36.1%—
Kagi LLM Benchmark61.3%—
NYT Connections (extended)—89.6%
ARC-AGI-15.5%—
Epoch Capabilities Index138.33—

Math Grok 4.20 Multi-Agent leads

Grok 3: 38.0 (#145), Grok 4.20 Multi-Agent: 39.4 (#104)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Math13911442
OTIS Mock AIME 2024-202555.6%—
Omni-MATH46.4%—
MATH Level 588.7%—
FrontierMath (Feb 2025 set)3.8%—
FrontierMath Tier 4 (v1)0%—

Knowledge Grok 3 leads

Grok 3: 46.2 (#82), Grok 4.20 Multi-Agent: 40.4 (#119)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Expert14211445
GPQA Diamond75.8%—
MMLU-Pro78.8%—
Confabulations14.2%—
Vectara Hallucination Rate5.8%—
GPQA (HELM)65%—

Multimodal Not comparable

Grok 3: —, Grok 4.20 Multi-Agent: 40.5 (#48)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Vision—1259

Multilingual Grok 4.20 Multi-Agent leads

Grok 3: 52.3 (#87), Grok 4.20 Multi-Agent: 54.4 (#43)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Non-English14101440
LMArena Chinese14481475
LMArena French14601466
LMArena German14311456
LMArena Japanese13871405
LMArena Korean13731416
LMArena Russian14161457
LMArena Spanish14171447

Instruction Following Too close to call

Grok 3: 75.0 (#73), Grok 4.20 Multi-Agent: 74.8 (#84)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Instruction Following14091420
IFEval88.4%—

Long Context Grok 4.20 Multi-Agent leads

Grok 3: 38.7 (#192), Grok 4.20 Multi-Agent: 43.7 (#88)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Longer Query14391431
Fiction.LiveBench58.3%—

Writing & Preference Grok 4.20 Multi-Agent leads

Grok 3: 55.8 (#141), Grok 4.20 Multi-Agent: 64.0 (#59)

BenchmarkGrok 3Grok 4.20 Multi-Agent
LMArena Text14261450
LMArena Creative Writing14141436
LMArena Multi-Turn14251452
Short-Story Creative Writing76.4%—
EQ-Bench Creative Writing1186—
WildBench84.9%—

Frequently asked questions

Is Grok 3 better than Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 39.9 on the Noometry Index.

Is Grok 3 or Grok 4.20 Multi-Agent better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 41.9 in the Noometry coding category.

How many benchmarks do Grok 3 and Grok 4.20 Multi-Agent share?

17 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Grok 4.20 Multi-Agent has 20.

Related comparisons

Go deeper