Noometry

Model comparison

Grok 4.7 vs Llama 2-70B

Grok 4.7 is the stronger model overall, scoring 53.1 to 24.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok 4.7 scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.7 leads 62.8 to 7.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.1% for Grok 4.7 and 0% for Llama 2-70B.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Grok 4.7Llama 2-70B
ProviderxAIMeta
Noometry Index53.124.4
Released2026-09-212023-07-18
WeightsProprietaryOpen
Context window500K—
Max output500K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked3935

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

Category by category

Coding Grok 4.7 leads

Grok 4.7: 58.0 (#18), Llama 2-70B: 31.4 (#286)

BenchmarkGrok 4.7Llama 2-70B
LMArena Coding14271079
FrontierCode47.6%—
CursorBench46.3%—
LMArena WebDev1639—
FrontierSWE29.5%—
SciCode57.8%—

Agentic & Tool Use Not comparable

Grok 4.7: 36.7 (#37), Llama 2-70B: —

BenchmarkGrok 4.7Llama 2-70B
APEX-Agents54.6%—
GDP.pdf22.8%—
Vending-Bench 210,537—

Reasoning Grok 4.7 leads

Grok 4.7: 49.1 (#40), Llama 2-70B: 14.4 (#325)

BenchmarkGrok 4.7Llama 2-70B
LMArena Hard Prompts14131073
DTBench96%41.6%
Epoch Capabilities Index153.53113.79
NYT Connections (extended)76.8%—
CritPt18%—
Chess Puzzles38%—
Mystery Game Puzzles29%—
LMCA49.4%—
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
PIQA—82.8%
WinoGrande—80.2%

Math Grok 4.7 leads

Grok 4.7: 57.8 (#39), Llama 2-70B: 8.1 (#326)

BenchmarkGrok 4.7Llama 2-70B
OTIS Mock AIME 2024-202598.1%0%
LMArena Math14071091
FrontierMath (Tiers 1-3)53%—
FrontierMath Tier 417.1%—
ProofBench34%—
MATH Level 5—3.3%
GSM8K—69.6%

Knowledge Grok 4.7 leads

Grok 4.7: 62.8 (#22), Llama 2-70B: 7.4 (#310)

BenchmarkGrok 4.7Llama 2-70B
GPQA Diamond92.7%26.3%
LMArena Expert14221039
SimpleQA Verified56%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
MMLU—69.9%
OpenBookQA—60.2%
TriviaQA—87.6%

Multimodal Not comparable

Grok 4.7: 35.5 (#87), Llama 2-70B: —

BenchmarkGrok 4.7Llama 2-70B
LMArena Vision1228—
Blueprint-Bench 232.5%—
Furniture Assembly20.8%—

Multilingual Grok 4.7 leads

Grok 4.7: 50.8 (#116), Llama 2-70B: 27.7 (#274)

BenchmarkGrok 4.7Llama 2-70B
LMArena Non-English13891045
LMArena Chinese1455995
LMArena French14551090
LMArena Russian13971083
LMArena Spanish14001143
LMArena German—1041
LMArena Japanese—927
LMArena Korean—964

Instruction Following Grok 4.7 leads

Grok 4.7: 74.1 (#105), Llama 2-70B: 54.9 (#278)

BenchmarkGrok 4.7Llama 2-70B
LMArena Instruction Following14041071

Long Context Grok 4.7 leads

Grok 4.7: 43.1 (#104), Llama 2-70B: 32.3 (#270)

BenchmarkGrok 4.7Llama 2-70B
LMArena Longer Query14131062

Writing & Preference Grok 4.7 leads

Grok 4.7: 70.0 (#24), Llama 2-70B: 32.3 (#279)

BenchmarkGrok 4.7Llama 2-70B
LMArena Text13991115
LMArena Creative Writing13911075
LMArena Multi-Turn13931088
EQ-Bench Creative Writing2007—

Frequently asked questions

Is Grok 4.7 better than Llama 2-70B?

Grok 4.7 is the stronger model overall, scoring 53.1 to 24.4 on the Noometry Index.

Is Grok 4.7 or Llama 2-70B better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 31.4 in the Noometry coding category.

How many benchmarks do Grok 4.7 and Llama 2-70B share?

18 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper