Noometry

Model comparison

Grok 4.7 vs Llama 3-70B

Grok 4.7 is the stronger model overall, scoring 53.1 to 28.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok 4.7 xAI

53.1

Rank #37 Confirmed

Llama 3-70B Meta

28.8

Rank #323 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok 4.7 scores higher in 9 categories and Llama 3-70B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.7 leads 57.8 to 12.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.1% for Grok 4.7 and 4.3% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

Grok 4.7Llama 3-70B
ProviderxAIMeta
Noometry Index53.128.8
Released2026-09-212024-04-18
WeightsProprietaryOpen
Context window500K—
Max output500K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked3931

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 3-70B: 35.8 (#218)

BenchmarkGrok 4.7Llama 3-70B
LMArena Coding14271206
FrontierCode47.6%—
CursorBench46.3%—
LMArena WebDev1639—
FrontierSWE29.5%—
SciCode57.8%—
BigCodeBench Instruct—43.6%
BigCodeBench Complete—54.5%
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use Grok 4.7 leads

Grok 4.7: 36.7 (#37), Llama 3-70B: 21.1 (#139)

BenchmarkGrok 4.7Llama 3-70B
APEX-Agents54.6%—
Cybench—5%
GDP.pdf22.8%—
Vending-Bench 210,537—

Reasoning Grok 4.7 leads

Grok 4.7: 49.1 (#40), Llama 3-70B: 18.0 (#288)

BenchmarkGrok 4.7Llama 3-70B
LMArena Hard Prompts14131195
DTBench96%54.2%
Epoch Capabilities Index153.53122.93
Kagi LLM Benchmark—35.1%
NYT Connections (extended)76.8%—
CritPt18%—
Chess Puzzles38%—
Mystery Game Puzzles29%—
LMCA49.4%—
ForecastBench—57.1
WinoGrande—83.5%

Math Grok 4.7 leads

Grok 4.7: 57.8 (#39), Llama 3-70B: 12.8 (#305)

BenchmarkGrok 4.7Llama 3-70B
OTIS Mock AIME 2024-202598.1%4.3%
LMArena Math14071218
FrontierMath (Tiers 1-3)53%—
FrontierMath Tier 417.1%—
ProofBench34%—
MATH Level 5—22.6%

Knowledge Grok 4.7 leads

Grok 4.7: 62.8 (#22), Llama 3-70B: 20.8 (#277)

BenchmarkGrok 4.7Llama 3-70B
GPQA Diamond92.7%40.6%
LMArena Expert14221149
SimpleQA Verified56%—
MMLU—79.3%

Multimodal Not comparable

Grok 4.7: 35.5 (#87), Llama 3-70B: —

BenchmarkGrok 4.7Llama 3-70B
LMArena Vision1228—
Blueprint-Bench 232.5%—
Furniture Assembly20.8%—

Multilingual Grok 4.7 leads

Grok 4.7: 50.8 (#116), Llama 3-70B: 33.6 (#251)

BenchmarkGrok 4.7Llama 3-70B
LMArena Non-English13891142
LMArena Chinese14551114
LMArena French14551232
LMArena Russian13971159
LMArena Spanish14001241
LMArena German—1169
LMArena Japanese—1017
LMArena Korean—1017

Instruction Following Grok 4.7 leads

Grok 4.7: 74.1 (#105), Llama 3-70B: 62.5 (#238)

BenchmarkGrok 4.7Llama 3-70B
LMArena Instruction Following14041194

Long Context Grok 4.7 leads

Grok 4.7: 43.1 (#104), Llama 3-70B: 35.6 (#240)

BenchmarkGrok 4.7Llama 3-70B
LMArena Longer Query14131174

Writing & Preference Grok 4.7 leads

Grok 4.7: 70.0 (#24), Llama 3-70B: 42.8 (#231)

BenchmarkGrok 4.7Llama 3-70B
LMArena Text13991221
LMArena Creative Writing13911210
LMArena Multi-Turn13931223
EQ-Bench Creative Writing2007—

Frequently asked questions

Is Grok 4.7 better than Llama 3-70B?

Grok 4.7 is the stronger model overall, scoring 53.1 to 28.8 on the Noometry Index.

Is Grok 4.7 or Llama 3-70B better for coding?

Grok 4.7 scores higher on coding benchmarks: 58.0 versus 35.8 in the Noometry coding category.

How many benchmarks do Grok 4.7 and Llama 3-70B share?

18 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper