Noometry

Model comparison

Grok 4 vs Grok 4.20 Multi-Agent

Grok 4 is the stronger model overall, scoring 48.1 to 46.2 on the Noometry Index.

Last verified . 19 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Grok 4.20 Multi-Agent xAI

46.2

Rank #65 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Grok 4 scores higher in 5 categories and Grok 4.20 Multi-Agent in 4 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 43.7.

Side by side

Grok 4Grok 4.20 Multi-Agent
ProviderxAIxAI
Noometry Index48.146.2
Released2025-07-092026-03-09
WeightsProprietaryProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked4820

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

Category by category

Coding Grok 4 leads

Grok 4: 50.3 (#46), Grok 4.20 Multi-Agent: 43.0 (#92)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Coding14081457
Aider Polyglot79.6%—
WeirdML45.7%—

Agentic & Tool Use Not comparable

Grok 4: 32.3 (#68), Grok 4.20 Multi-Agent: —

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Search11421204
Terminal-Bench27.2%—
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
METR Time Horizons66.6%—

Reasoning Grok 4.20 Multi-Agent leads

Grok 4: 36.7 (#65), Grok 4.20 Multi-Agent: 43.9 (#48)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Hard Prompts14091448
ARC-AGI-216%—
SimpleBench60.5%—
Kagi LLM Benchmark73.6%—
NYT Connections (extended)—89.6%
ARC-AGI-166.7%—
Chess Puzzles28%—
Epoch Capabilities Index146.44—
ForecastBench60.9—

Math Grok 4 leads

Grok 4: 48.4 (#64), Grok 4.20 Multi-Agent: 39.4 (#104)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Math14221442
OTIS Mock AIME 2024-202584%—
Omni-MATH60.3%—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), Grok 4.20 Multi-Agent: 40.4 (#119)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Expert14151445
GPQA Diamond87%—
MMLU-Pro85.1%—
Confabulations12.4%—
GPQA (HELM)72.7%—

Multimodal Grok 4.20 Multi-Agent leads

Grok 4: 33.7 (#94), Grok 4.20 Multi-Agent: 40.5 (#48)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Vision12101259
GeoBench45%—

Multilingual Grok 4.20 Multi-Agent leads

Grok 4: 51.8 (#103), Grok 4.20 Multi-Agent: 54.4 (#43)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Non-English14031440
LMArena Chinese14271475
LMArena French14181466
LMArena German14291456
LMArena Japanese13941405
LMArena Korean13771416
LMArena Russian14101457
LMArena Spanish14201447

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Grok 4.20 Multi-Agent: 74.8 (#84)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Instruction Following13871420
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Grok 4.20 Multi-Agent: 43.7 (#88)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Longer Query14091431
Fiction.LiveBench94.4%—

Writing & Preference Grok 4.20 Multi-Agent leads

Grok 4: 58.5 (#116), Grok 4.20 Multi-Agent: 64.0 (#59)

BenchmarkGrok 4Grok 4.20 Multi-Agent
LMArena Text14111450
LMArena Creative Writing13971436
LMArena Multi-Turn14161452
Short-Story Creative Writing76.9%—
WildBench79.7%—

Frequently asked questions

Is Grok 4 better than Grok 4.20 Multi-Agent?

Grok 4 is the stronger model overall, scoring 48.1 to 46.2 on the Noometry Index.

Is Grok 4 or Grok 4.20 Multi-Agent better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 43.0 in the Noometry coding category.

How many benchmarks do Grok 4 and Grok 4.20 Multi-Agent share?

19 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Grok 4.20 Multi-Agent has 20.

Related comparisons

Go deeper