Noometry

Model comparison

Grok 4.20 Multi-Agent vs Llama 2-13B

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 29.1 on the Noometry Index.

Last verified . 17 shared benchmarks.

Grok 4.20 Multi-Agent xAI

45.5

Rank #62 Confirmed

Llama 2-13B Meta

29.1

Rank #304 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 8 categories and Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok 4.20 Multi-Agent leads 64.1 to 30.0.
  • Llama 2-13B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 Multi-AgentLlama 2-13B
ProviderxAIMeta
Noometry Index45.529.1
Released2026-03-092023-07-18
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked2032

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: 42.4 (#91), Llama 2-13B: 30.4 (#287)

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Coding14581062

Agentic & Tool Use Not comparable

Grok 4.20 Multi-Agent: —, Llama 2-13B: —

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Search1204—

Reasoning Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 42.4 (#44), Llama 2-13B: 12.3 (#333)

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Hard Prompts14481051
NYT Connections (extended)89.6%—
Chess Puzzles—0%
DTBench—42.2%
BIG-Bench Hard—58.2%
Epoch Capabilities Index—105.8
HellaSwag—80.7%
LAMBADA—76.5%
PIQA—80.8%
WinoGrande—72.8%

Math Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 36.6 (#106), Llama 2-13B: 28.7 (#226)

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Math14411065
GSM8K—36.9%

Knowledge Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 39.7 (#116), Llama 2-13B: 27.5 (#244)

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Expert14451030
ARC (AI2) Challenge—60.3%
BoolQ—82.4%
MMLU—55.6%
OpenBookQA—57%
TriviaQA—79.6%

Multimodal Not comparable

Grok 4.20 Multi-Agent: 39.8 (#44), Llama 2-13B: —

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Vision1259—
ScienceQA—55.8%

Multilingual Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 54.6 (#40), Llama 2-13B: 26.7 (#274)

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Non-English14401024
LMArena Chinese14751001
LMArena French14671043
LMArena German14561009
LMArena Japanese1405894
LMArena Korean1416953
LMArena Russian14571055
LMArena Spanish14471086

Instruction Following Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 75.0 (#80), Llama 2-13B: 53.5 (#282)

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Instruction Following14201046

Long Context Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.7 (#84), Llama 2-13B: 32.3 (#264)

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Longer Query14301064

Writing & Preference Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 64.1 (#57), Llama 2-13B: 30.0 (#284)

BenchmarkGrok 4.20 Multi-AgentLlama 2-13B
LMArena Text14501085
LMArena Creative Writing14351047
LMArena Multi-Turn14511050

Frequently asked questions

Is Grok 4.20 Multi-Agent better than Llama 2-13B?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 29.1 on the Noometry Index.

Is Grok 4.20 Multi-Agent or Llama 2-13B better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 30.4 in the Noometry coding category.

How many benchmarks do Grok 4.20 Multi-Agent and Llama 2-13B share?

17 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Llama 2-13B has 32.

Related comparisons

Go deeper