Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Llama 3-8B

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 25.5 on the Noometry Index.

Last verified . 23 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Llama 3-8B Meta

25.5

Rank #344 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 7.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Grok 4.20 (Non-Reasoning) and 1.9% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Llama 3-8B
ProviderxAIMeta
Noometry Index48.625.5
Released2026-02-172024-04-18
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked4634

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 42.1 (#112), Llama 3-8B: 31.0 (#289)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
LMArena Coding14591152
LMArena WebDev1375—
WeirdML52.3%—
BigCodeBench Instruct—31.9%
BigCodeBench Complete—36.9%
ALE-Bench1,150—
HumanEval+—56.7%
MBPP+—54.8%

Agentic & Tool Use Not comparable

Grok 4.20 (Non-Reasoning): 34.4 (#46), Llama 3-8B: —

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
Terminal-Bench57.3%—
τ²-bench Banking18%—
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Llama 3-8B: 14.3 (#326)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
Chess Puzzles24%0%
LMArena Hard Prompts14511133
DTBench90.1%43.9%
Epoch Capabilities Index151.98116.45
ForecastBench61.458.6
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
Thematic Generalization63.8%—
LMCA38.7%—
Adversarial NLI—57.3%
WinoGrande—75.7%

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Llama 3-8B: 8.8 (#323)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
OTIS Mock AIME 2024-202592.2%1.9%
LMArena Math14551151
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
ProofBench14%—
MATH Level 5—6.1%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Llama 3-8B: 7.8 (#308)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
GPQA Diamond89.3%26.1%
LMArena Expert14391113
SimpleQA Verified30.2%—
ARC (AI2) Challenge—82.8%
MMLU—68.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Llama 3-8B: —

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Llama 3-8B: 30.8 (#261)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
LMArena Non-English14411098
LMArena Chinese14811076
LMArena French14761159
LMArena German14651104
LMArena Japanese1449967
LMArena Korean14171004
LMArena Russian14581109
LMArena Spanish14431173

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Llama 3-8B: 58.4 (#260)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
LMArena Instruction Following14201127

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Llama 3-8B: 34.2 (#251)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
LMArena Longer Query14371128
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Llama 3-8B: 37.5 (#256)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 3-8B
LMArena Text14511166
LMArena Creative Writing14381150
LMArena Multi-Turn14561152
EQ-Bench Creative Writing1574—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Llama 3-8B?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 25.5 on the Noometry Index.

Is Grok 4.20 (Non-Reasoning) or Llama 3-8B better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 31.0 in the Noometry coding category.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 3-8B share?

23 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper