Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Llama 4 Scout

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 27.7 on the Noometry Index. Llama 4 Scout costs 10× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Last verified . 28 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Llama 4 Scout Meta

27.7

Rank #330 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 10 categories and Llama 4 Scout in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 9.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 89.5% for Grok 4.20 (Non-Reasoning) and 0.5% for Llama 4 Scout.
  • Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
  • Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 128K.
  • Llama 4 Scout has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Llama 4 Scout
ProviderxAIMeta
Noometry Index48.627.7
Released2026-02-172025-04-05
WeightsProprietaryOpen
Context window1M128K
Max output30K4K
Input $ / M tokens$1.25$0.10
Output $ / M tokens$2.50$0.30
Results tracked4643

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 4 Scout: 20.2 (#339)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
LMArena Coding14591286
SWE-bench Verified (bash only)—9.1%
LMArena WebDev1375—
SciCode—17%
WeirdML52.3%—
BigCodeBench Complete—43.1%
ALE-Bench1,150—

Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 34.4 (#46), Llama 4 Scout: 24.6 (#119)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
Terminal-Bench57.3%—
Berkeley Function Calling Leaderboard—28.1%
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 4 Scout: 9.1 (#345)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
ARC-AGI-265.1%0%
Kagi LLM Benchmark75%36.9%
ARC-AGI-189.5%0.5%
LMArena Hard Prompts14511266
DTBench90.1%57.9%
LMCA38.7%12%
Epoch Capabilities Index151.98129.64
ForecastBench61.457.5
NYT Connections (extended)85.4%—
CritPt—0%
Chess Puzzles24%—
Thematic Generalization63.8%—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Llama 4 Scout: 19.6 (#286)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
OTIS Mock AIME 2024-202592.2%7.8%
LMArena Math14551287
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
ProofBench14%—
Omni-MATH—37.3%
MATH Level 5—62.3%
FrontierMath (Feb 2025 set)—0%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Llama 4 Scout: 31.9 (#217)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
GPQA Diamond89.3%51.8%
LMArena Expert14391235
SimpleQA Verified30.2%—
MMLU-Pro—74.2%
Vectara Hallucination Rate—7.7%
GPQA (HELM)—50.7%

Multimodal Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 33.3 (#98), Llama 4 Scout: 32.2 (#102)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
LMArena Vision12631118
Blueprint-Bench 20%—
LMArena Document1416—
SpatialViz-Bench—34.2%

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Llama 4 Scout: 41.0 (#212)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
LMArena Non-English14411252
LMArena Chinese14811255
LMArena French14761282
LMArena German14651272
LMArena Japanese14491206
LMArena Korean14171207
LMArena Russian14581263
LMArena Spanish14431278

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Llama 4 Scout: 65.8 (#217)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
LMArena Instruction Following14201248
IFEval—81.8%

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Llama 4 Scout: 27.5 (#294)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
LMArena Longer Query14371265
Fiction.LiveBench—36%
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Llama 4 Scout: 37.0 (#261)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Scout
LMArena Text14511279
LMArena Creative Writing14381249
EQ-Bench Creative Writing1574783
LMArena Multi-Turn14561280
WildBench—78%

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Llama 4 Scout?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 27.7 on the Noometry Index. Llama 4 Scout costs 10× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Which is cheaper, Grok 4.20 (Non-Reasoning) or Llama 4 Scout?

Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Grok 4.20 (Non-Reasoning) or Llama 4 Scout better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 20.2 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 4 Scout share?

28 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 4 Scout has 43.

Related comparisons

Go deeper