Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Llama 2-7B

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 29.1 on the Noometry Index.

Last verified . 17 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Llama 2-7B Meta

29.1

Rank #317 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Llama 2-7B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok 4.20 (Non-Reasoning) leads 65.7 to 28.0.
  • The biggest single-benchmark swing is Chess Puzzles: 24% for Grok 4.20 (Non-Reasoning) and 0% for Llama 2-7B.
  • Llama 2-7B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Llama 2-7B
ProviderxAIMeta
Noometry Index48.629.1
Released2026-02-172023-07-18
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked4629

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 2-7B: 29.2 (#307)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
LMArena Coding14591002
LMArena WebDev1375—
WeirdML52.3%—
ALE-Bench1,150—

Agentic & Tool Use Not comparable

Grok 4.20 (Non-Reasoning): 34.4 (#46), Llama 2-7B: —

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
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 2-7B: 15.7 (#312)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
Chess Puzzles24%0%
LMArena Hard Prompts14511009
Epoch Capabilities Index151.9899.06
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
Thematic Generalization63.8%—
DTBench90.1%—
LMCA38.7%—
BIG-Bench Hard—39.2%
ForecastBench61.4—
HellaSwag—77.2%
LAMBADA—73.3%
PIQA—78.8%
WinoGrande—69.2%

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Llama 2-7B: 30.7 (#233)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
LMArena Math14551042
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202592.2%—
ProofBench14%—
GSM8K—16.7%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Llama 2-7B: 28.2 (#248)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
LMArena Expert14391036
GPQA Diamond89.3%—
SimpleQA Verified30.2%—
ARC (AI2) Challenge—45.9%
BoolQ—77.9%
MMLU—45.8%
OpenBookQA—58.6%
TriviaQA—73.7%

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Llama 2-7B: —

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—
ScienceQA—43.1%

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Llama 2-7B: 23.8 (#293)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
LMArena Non-English1441973
LMArena Chinese1481973
LMArena French1476970
LMArena German1465978
LMArena Russian1458995
LMArena Spanish14431007
LMArena Japanese1449—
LMArena Korean1417—

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Llama 2-7B: 50.8 (#298)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
LMArena Instruction Following14201006

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Llama 2-7B: 30.4 (#287)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
LMArena Longer Query1437999
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Llama 2-7B: 28.0 (#298)

BenchmarkGrok 4.20 (Non-Reasoning)Llama 2-7B
LMArena Text14511053
LMArena Creative Writing14381033
LMArena Multi-Turn14561029
EQ-Bench Creative Writing1574—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Llama 2-7B?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 29.1 on the Noometry Index.

Is Grok 4.20 (Non-Reasoning) or Llama 2-7B better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 29.2 in the Noometry coding category.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Llama 2-7B share?

17 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Llama 2-7B has 29.

Related comparisons

Go deeper