Noometry

Model comparison

Grok 4.20 Multi-Agent vs Step 3

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 40.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

Grok 4.20 Multi-Agent xAI

46.2

Rank #65 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 28.4.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 Multi-AgentStep 3
ProviderxAIStepFun
Noometry Index46.240.5
Released2026-03-09—
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked2017

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

Category by category

Coding Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.0 (#92), Step 3: 40.1 (#147)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Coding14571367

Agentic & Tool Use Not comparable

Grok 4.20 Multi-Agent: —, Step 3: —

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Search1204—

Reasoning Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.9 (#48), Step 3: 28.4 (#105)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Hard Prompts14481355
Kagi LLM Benchmark—62.3%
NYT Connections (extended)89.6%—

Math Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 39.4 (#104), Step 3: 37.6 (#148)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Math14421366

Knowledge Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 40.4 (#119), Step 3: 36.8 (#164)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Expert14451333

Multimodal Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 40.5 (#48), Step 3: 35.5 (#86)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Vision12591177

Multilingual Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 54.4 (#43), Step 3: 46.3 (#159)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Non-English14401327
LMArena Chinese14751397
LMArena German14561371
LMArena Korean14161269
LMArena Russian14571331
LMArena Spanish14471371
LMArena French1466—
LMArena Japanese1405—

Instruction Following Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 74.8 (#84), Step 3: 70.4 (#164)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Instruction Following14201332

Long Context Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.7 (#88), Step 3: 40.3 (#157)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Longer Query14311326

Writing & Preference Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 64.0 (#59), Step 3: 54.3 (#151)

BenchmarkGrok 4.20 Multi-AgentStep 3
LMArena Text14501350
LMArena Creative Writing14361321
LMArena Multi-Turn14521341

Frequently asked questions

Is Grok 4.20 Multi-Agent better than Step 3?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 40.5 on the Noometry Index.

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

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 40.1 in the Noometry coding category.

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

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

Related comparisons

Go deeper