Noometry

Model comparison

Grok 4.3 vs Llama 3-70B

Grok 4.3 is the stronger model overall, scoring 43.6 to 28.5 on the Noometry Index.

Last verified . 22 shared benchmarks.

Grok 4.3 xAI

43.6

Rank #80 Confirmed

Llama 3-70B Meta

28.5

Rank #317 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Grok 4.3 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 4.3 leads 45.8 to 12.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for Grok 4.3 and 4.3% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

Grok 4.3Llama 3-70B
ProviderxAIMeta
Noometry Index43.628.5
Released2026-04-172024-04-18
WeightsProprietaryOpen
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked4031

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

Category by category

Coding Grok 4.3 leads

Grok 4.3: 41.3 (#117), Llama 3-70B: 35.3 (#215)

BenchmarkGrok 4.3Llama 3-70B
LMArena Coding14151206
LMArena WebDev1357—
SciCode47.3%—
WeirdML49.9%—
BigCodeBench Instruct—43.6%
BigCodeBench Complete—54.5%
ALE-Bench944.17—
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use Grok 4.3 leads

Grok 4.3: 27.6 (#93), Llama 3-70B: 20.9 (#132)

BenchmarkGrok 4.3Llama 3-70B
Cybench—5%
GDP.pdf8%—
LMArena Search1165—
Vending-Bench 235.26—

Reasoning Grok 4.3 leads

Grok 4.3: 34.9 (#60), Llama 3-70B: 17.4 (#284)

BenchmarkGrok 4.3Llama 3-70B
LMArena Hard Prompts13971195
DTBench90.7%54.2%
Epoch Capabilities Index149.13122.91
ForecastBench60.357.1
Kagi LLM Benchmark—35.1%
NYT Connections (extended)55.2%—
CritPt8%—
Chess Puzzles25%—
LMCA38.3%—
WinoGrande—83.5%

Math Grok 4.3 leads

Grok 4.3: 45.8 (#60), Llama 3-70B: 12.0 (#299)

BenchmarkGrok 4.3Llama 3-70B
OTIS Mock AIME 2024-202593.3%4.3%
LMArena Math13881218
FrontierMath (Tiers 1-3)42.8%—
FrontierMath Tier 414.6%—
ProofBench11%—
MATH Level 5—22.6%

Knowledge Grok 4.3 leads

Grok 4.3: 52.5 (#57), Llama 3-70B: 20.8 (#272)

BenchmarkGrok 4.3Llama 3-70B
GPQA Diamond88.8%40.6%
LMArena Expert13851149
SimpleQA Verified33.2%—
MMLU—79.3%

Multimodal Not comparable

Grok 4.3: 31.6 (#96), Llama 3-70B: —

BenchmarkGrok 4.3Llama 3-70B
LMArena Vision1231—
Blueprint-Bench 20%—

Multilingual Grok 4.3 leads

Grok 4.3: 50.7 (#114), Llama 3-70B: 33.8 (#246)

BenchmarkGrok 4.3Llama 3-70B
LMArena Non-English13851142
LMArena Chinese14231114
LMArena French14121231
LMArena German13951169
LMArena Japanese13791017
LMArena Korean13571017
LMArena Russian13991159
LMArena Spanish14021241

Instruction Following Grok 4.3 leads

Grok 4.3: 72.3 (#135), Llama 3-70B: 62.8 (#233)

BenchmarkGrok 4.3Llama 3-70B
LMArena Instruction Following13661194

Long Context Grok 4.3 leads

Grok 4.3: 42.5 (#118), Llama 3-70B: 35.6 (#235)

BenchmarkGrok 4.3Llama 3-70B
LMArena Longer Query13931174

Writing & Preference Grok 4.3 leads

Grok 4.3: 58.6 (#112), Llama 3-70B: 43.0 (#225)

BenchmarkGrok 4.3Llama 3-70B
LMArena Text13971221
LMArena Creative Writing13801210
LMArena Multi-Turn14061223
EQ-Bench 41075—

Frequently asked questions

Is Grok 4.3 better than Llama 3-70B?

Grok 4.3 is the stronger model overall, scoring 43.6 to 28.5 on the Noometry Index.

Is Grok 4.3 or Llama 3-70B better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.3 versus 35.3 in the Noometry coding category.

How many benchmarks do Grok 4.3 and Llama 3-70B share?

22 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper