Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Llama 4 Maverick

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 30.6 on the Noometry Index. Llama 4 Maverick costs 5.1× 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 . 31 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.5

Rank #48 Confirmed

Llama 4 Maverick Meta

30.6

Rank #276 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 10.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 89.5% for Grok 4.20 (Non-Reasoning) and 4.4% for Llama 4 Maverick.
  • Llama 4 Maverick is cheaper at $0.19 / $0.65 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 Maverick has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Llama 4 Maverick
ProviderxAIMeta
Noometry Index48.530.6
Released2026-02-172025-04-05
WeightsProprietaryOpen
Context window1M128K
Max output30K4K
Input $ / M tokens$1.25$0.19
Output $ / M tokens$2.50$0.65
Results tracked4654

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): 41.8 (#104), Llama 4 Maverick: 26.3 (#318)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
WeirdML52.3%24.5%
LMArena Coding14581302
ALE-Bench1,150172.97
SWE-bench Verified (bash only)—21%
Aider Polyglot—15.6%
LMArena WebDev1374—
SciCode—33.1%
BigCodeBench Instruct—49.7%
BigCodeBench Complete—61.4%

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

Grok 4.20 (Non-Reasoning): 34.3 (#43), Llama 4 Maverick: 27.9 (#86)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
Terminal-Bench57.3%—
Berkeley Function Calling Leaderboard—37.3%
τ²-bench Banking18%—
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.2 (#30), Llama 4 Maverick: 10.1 (#337)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
ARC-AGI-265.1%0%
Kagi LLM Benchmark75%55.9%
NYT Connections (extended)85.4%8%
ARC-AGI-189.5%4.4%
LMArena Hard Prompts14511281
DTBench90.1%61.9%
LMCA38.7%15.9%
Epoch Capabilities Index152.01132.2
ForecastBench61.457.5
SimpleBench—27.7%
CritPt—0%
Chess Puzzles24%—
EnigmaEval—0.6%
Thematic Generalization63.8%—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.0 (#54), Llama 4 Maverick: 24.6 (#256)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
OTIS Mock AIME 2024-202592.2%20.6%
LMArena Math14551299
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
ProofBench14%—
Omni-MATH—42.2%
MATH Level 5—73%
FrontierMath (Feb 2025 set)—0.7%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#54), Llama 4 Maverick: 33.3 (#196)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
GPQA Diamond89.3%67%
LMArena Expert14401259
Humanity's Last Exam—5.7%
SimpleQA Verified30.2%—
MMLU-Pro—81%
Confabulations—22.6%
Vectara Hallucination Rate—8.2%
GPQA (HELM)—65%

Multimodal Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 33.2 (#88), Llama 4 Maverick: 30.9 (#100)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
LMArena Vision12631141
GeoBench—52%
Blueprint-Bench 20%—
LMArena Document1416—
SpatialViz-Bench—31.8%

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.7 (#38), Llama 4 Maverick: 42.4 (#190)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
LMArena Non-English14401269
LMArena Chinese14811277
LMArena French14771258
LMArena German14631291
LMArena Japanese14501207
LMArena Korean14171203
LMArena Russian14571286
LMArena Spanish14421293

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 75.0 (#79), Llama 4 Maverick: 71.9 (#140)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
LMArena Instruction Following14201267
IFEval—90.8%

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.4 (#33), Llama 4 Maverick: 31.4 (#274)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
LMArena Longer Query14361280
Fiction.LiveBench—46.2%
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.9 (#42), Llama 4 Maverick: 39.0 (#247)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 4 Maverick
LMArena Text14511287
LMArena Creative Writing14391266
EQ-Bench Creative Writing1574860
LMArena Multi-Turn14561289
Short-Story Creative Writing—62%
WildBench—80%

Frequently asked questions

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

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 30.6 on the Noometry Index. Llama 4 Maverick costs 5.1× 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 Maverick?

Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 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 Maverick better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 26.3 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 Maverick share?

31 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 4 Maverick has 54.

Related comparisons

Go deeper