Noometry

Model comparison

Grok 4.1 Fast vs Llama 3-70B

Grok 4.1 Fast is the stronger model overall, scoring 40.9 to 28.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

Grok 4.1 Fast xAI

40.9

Rank #131 Confirmed

Llama 3-70B Meta

28.5

Rank #317 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Grok 4.1 Fast scores higher in 8 categories and Llama 3-70B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.1 Fast leads 42.3 to 17.4.
  • The biggest single-benchmark swing is DTBench: 87.7% for Grok 4.1 Fast and 54.2% for Llama 3-70B.
  • Llama 3-70B has downloadable open weights; the other is API-only.

Side by side

Grok 4.1 FastLlama 3-70B
ProviderxAIMeta
Noometry Index40.928.5
Released2025-06-272024-04-18
WeightsProprietaryOpen
Context window128K—
Max output30K—
Input $ / M tokens$0.20—
Output $ / M tokens$0.50—
Results tracked3231

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

Category by category

Coding Llama 3-70B leads

Grok 4.1 Fast: 33.8 (#236), Llama 3-70B: 35.3 (#215)

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Coding14111206
LMArena WebDev1241—
BigCodeBench Instruct—43.6%
BigCodeBench Complete—54.5%
ALE-Bench394.93—
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use Grok 4.1 Fast leads

Grok 4.1 Fast: 36.1 (#35), Llama 3-70B: 20.9 (#132)

BenchmarkGrok 4.1 FastLlama 3-70B
Berkeley Function Calling Leaderboard69.6%—
τ²-bench Banking13.1%—
Cybench—5%
LMArena Search1171—
Vending-Bench 21,107—

Reasoning Grok 4.1 Fast leads

Grok 4.1 Fast: 42.3 (#45), Llama 3-70B: 17.4 (#284)

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Hard Prompts14071195
DTBench87.7%54.2%
ForecastBench6157.1
SimpleBench56%—
Kagi LLM Benchmark—35.1%
NYT Connections (extended)87.4%—
Epoch Capabilities Index—122.91
WinoGrande—83.5%

Math Grok 4.1 Fast leads

Grok 4.1 Fast: 30.9 (#201), Llama 3-70B: 12.0 (#299)

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Math14081218
MathArena Final-Answer Competitions60.9%—
OTIS Mock AIME 2024-2025—4.3%
ProofBench4%—
MATH Level 5—22.6%

Knowledge Grok 4.1 Fast leads

Grok 4.1 Fast: 32.6 (#203), Llama 3-70B: 20.8 (#272)

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Expert13981149
GPQA Diamond—40.6%
Vectara Hallucination Rate17.8%—
MMLU—79.3%

Multimodal Not comparable

Grok 4.1 Fast: 36.3 (#71), Llama 3-70B: —

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Vision1201—

Multilingual Grok 4.1 Fast leads

Grok 4.1 Fast: 51.1 (#110), Llama 3-70B: 33.8 (#246)

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Non-English13911142
LMArena Chinese14411114
LMArena French14161231
LMArena German14041169
LMArena Japanese13471017
LMArena Korean13611017
LMArena Russian13871159
LMArena Spanish14111241

Instruction Following Grok 4.1 Fast leads

Grok 4.1 Fast: 72.8 (#127), Llama 3-70B: 62.8 (#233)

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Instruction Following13761194

Long Context Grok 4.1 Fast leads

Grok 4.1 Fast: 42.4 (#121), Llama 3-70B: 35.6 (#235)

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Longer Query13901174

Writing & Preference Grok 4.1 Fast leads

Grok 4.1 Fast: 57.4 (#126), Llama 3-70B: 43.0 (#225)

BenchmarkGrok 4.1 FastLlama 3-70B
LMArena Text14081221
LMArena Creative Writing13941210
LMArena Multi-Turn13891223
EQ-Bench Creative Writing1327—

Frequently asked questions

Is Grok 4.1 Fast better than Llama 3-70B?

Grok 4.1 Fast is the stronger model overall, scoring 40.9 to 28.5 on the Noometry Index.

Is Grok 4.1 Fast or Llama 3-70B better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.3 versus 33.8 in the Noometry coding category.

How many benchmarks do Grok 4.1 Fast and Llama 3-70B share?

19 benchmarks have published results for both models. Grok 4.1 Fast has 32 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper