Noometry

Model comparison

Grok 4.20 Multi-Agent vs Phi 3 Medium 4k Instruct

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 33.0 on the Noometry Index.

Last verified . 17 shared benchmarks.

Grok 4.20 Multi-Agent xAI

46.2

Rank #65 Confirmed

Phi 3 Medium 4k Instruct Microsoft

33.0

Rank #250 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 8 categories and Phi 3 Medium 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok 4.20 Multi-Agent leads 64.0 to 34.1.
  • Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
ProviderxAIMicrosoft
Noometry Index46.233.0
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), Phi 3 Medium 4k Instruct: 32.9 (#268)

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Coding14571130

Agentic & Tool Use Not comparable

Grok 4.20 Multi-Agent: —, Phi 3 Medium 4k Instruct: —

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Search1204—

Reasoning Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.9 (#48), Phi 3 Medium 4k Instruct: 21.7 (#214)

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Hard Prompts14481127
NYT Connections (extended)89.6%—

Math Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 39.4 (#104), Phi 3 Medium 4k Instruct: 33.4 (#202)

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Math14421173

Knowledge Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 40.4 (#119), Phi 3 Medium 4k Instruct: 30.2 (#229)

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Expert14451108

Multimodal Not comparable

Grok 4.20 Multi-Agent: 40.5 (#48), Phi 3 Medium 4k Instruct: —

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Vision1259—

Multilingual Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 54.4 (#43), Phi 3 Medium 4k Instruct: 30.6 (#263)

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Non-English14401094
LMArena Chinese14751108
LMArena French14661110
LMArena German14561101
LMArena Japanese14051042
LMArena Korean1416954
LMArena Russian14571145
LMArena Spanish14471095

Instruction Following Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 74.8 (#84), Phi 3 Medium 4k Instruct: 57.6 (#268)

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Instruction Following14201113

Long Context Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.7 (#88), Phi 3 Medium 4k Instruct: 34.0 (#255)

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Longer Query14311120

Writing & Preference Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 64.0 (#59), Phi 3 Medium 4k Instruct: 34.1 (#272)

BenchmarkGrok 4.20 Multi-AgentPhi 3 Medium 4k Instruct
LMArena Text14501138
LMArena Creative Writing14361107
LMArena Multi-Turn14521088

Frequently asked questions

Is Grok 4.20 Multi-Agent better than Phi 3 Medium 4k Instruct?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 33.0 on the Noometry Index.

Is Grok 4.20 Multi-Agent or Phi 3 Medium 4k Instruct better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 32.9 in the Noometry coding category.

How many benchmarks do Grok 4.20 Multi-Agent and Phi 3 Medium 4k Instruct share?

17 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.

Related comparisons

Go deeper