Noometry

Model comparison

Grok 4 vs Llama 3-70B

Grok 4 is the stronger model overall, scoring 48.1 to 28.8 on the Noometry Index.

Last verified . 23 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Llama 3-70B Meta

28.8

Rank #323 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Grok 4 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 leads 48.4 to 12.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84% for Grok 4 and 4.3% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

Grok 4Llama 3-70B
ProviderxAIMeta
Noometry Index48.128.8
Released2025-07-092024-04-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4831

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

Category by category

Coding Grok 4 leads

Grok 4: 50.3 (#46), Llama 3-70B: 35.8 (#218)

BenchmarkGrok 4Llama 3-70B
LMArena Coding14081206
Aider Polyglot79.6%—
WeirdML45.7%—
BigCodeBench Instruct—43.6%
BigCodeBench Complete—54.5%
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use Grok 4 leads

Grok 4: 32.3 (#68), Llama 3-70B: 21.1 (#139)

BenchmarkGrok 4Llama 3-70B
Cybench43%5%
Terminal-Bench27.2%—
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
DeepResearch Bench47.3%—
BALROG43.6%—
LMArena Search1142—
METR Time Horizons66.6%—

Reasoning Grok 4 leads

Grok 4: 36.7 (#65), Llama 3-70B: 18.0 (#288)

BenchmarkGrok 4Llama 3-70B
Kagi LLM Benchmark73.6%35.1%
LMArena Hard Prompts14091195
Epoch Capabilities Index146.44122.93
ForecastBench60.957.1
ARC-AGI-216%—
SimpleBench60.5%—
ARC-AGI-166.7%—
Chess Puzzles28%—
DTBench—54.2%
WinoGrande—83.5%

Math Grok 4 leads

Grok 4: 48.4 (#64), Llama 3-70B: 12.8 (#305)

BenchmarkGrok 4Llama 3-70B
OTIS Mock AIME 2024-202584%4.3%
LMArena Math14221218
Omni-MATH60.3%—
MATH Level 5—22.6%
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), Llama 3-70B: 20.8 (#277)

BenchmarkGrok 4Llama 3-70B
GPQA Diamond87%40.6%
LMArena Expert14151149
MMLU-Pro85.1%—
Confabulations12.4%—
GPQA (HELM)72.7%—
MMLU—79.3%

Multimodal Not comparable

Grok 4: 33.7 (#94), Llama 3-70B: —

BenchmarkGrok 4Llama 3-70B
LMArena Vision1210—
GeoBench45%—

Multilingual Grok 4 leads

Grok 4: 51.8 (#103), Llama 3-70B: 33.6 (#251)

BenchmarkGrok 4Llama 3-70B
LMArena Non-English14031142
LMArena Chinese14271114
LMArena French14181232
LMArena German14291169
LMArena Japanese13941017
LMArena Korean13771017
LMArena Russian14101159
LMArena Spanish14201241

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Llama 3-70B: 62.5 (#238)

BenchmarkGrok 4Llama 3-70B
LMArena Instruction Following13871194
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Llama 3-70B: 35.6 (#240)

BenchmarkGrok 4Llama 3-70B
LMArena Longer Query14091174
Fiction.LiveBench94.4%—

Writing & Preference Grok 4 leads

Grok 4: 58.5 (#116), Llama 3-70B: 42.8 (#231)

BenchmarkGrok 4Llama 3-70B
LMArena Text14111221
LMArena Creative Writing13971210
LMArena Multi-Turn14161223
Short-Story Creative Writing76.9%—
WildBench79.7%—

Frequently asked questions

Is Grok 4 better than Llama 3-70B?

Grok 4 is the stronger model overall, scoring 48.1 to 28.8 on the Noometry Index.

Is Grok 4 or Llama 3-70B better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 35.8 in the Noometry coding category.

How many benchmarks do Grok 4 and Llama 3-70B share?

23 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper