Noometry

Model comparison

Grok-2 (Dec 2024) vs Llama 3.1 Nemotron 70b Instruct

Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.0 to 33.4 on the Noometry Index.

Last verified . 12 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.4

Rank #233 Confirmed

Llama 3.1 Nemotron 70b Instruct NVIDIA

37.0

Rank #199 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 4 categories and Llama 3.1 Nemotron 70b Instruct in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Llama 3.1 Nemotron 70b Instruct leads 32.9 to 19.6.
  • Llama 3.1 Nemotron 70b Instruct has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
ProviderxAINVIDIA
Noometry Index33.437.0
Released2024-08-132024-12-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3414

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

Category by category

Coding Llama 3.1 Nemotron 70b Instruct leads

Grok-2 (Dec 2024): 32.9 (#254), Llama 3.1 Nemotron 70b Instruct: 35.3 (#212)

BenchmarkGrok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
LMArena Coding12881272
WeirdML22.2%—
BigCodeBench Instruct—38.7%
LiveBench Coding46.4%—
BigCodeBench Complete—48.2%

Reasoning Llama 3.1 Nemotron 70b Instruct leads

Grok-2 (Dec 2024): 16.4 (#294), Llama 3.1 Nemotron 70b Instruct: 24.0 (#156)

BenchmarkGrok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
LMArena Hard Prompts12721266
SimpleBench22.7%—
LiveBench Reasoning54.8%—
DTBench65.2%—
LiveBench Data Analysis54.5%—
Epoch Capabilities Index130.48—
LiveBench54.3%—

Math Llama 3.1 Nemotron 70b Instruct leads

Grok-2 (Dec 2024): 19.6 (#278), Llama 3.1 Nemotron 70b Instruct: 32.9 (#182)

BenchmarkGrok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
LMArena Math12831271
OTIS Mock AIME 2024-202511.5%—
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Llama 3.1 Nemotron 70b Instruct leads

Grok-2 (Dec 2024): 29.8 (#225), Llama 3.1 Nemotron 70b Instruct: 33.5 (#194)

BenchmarkGrok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
LMArena Expert12541242
GPQA Diamond53.8%—
Confabulations20.1%—

Multilingual Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 43.3 (#183), Llama 3.1 Nemotron 70b Instruct: 40.7 (#212)

BenchmarkGrok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
LMArena Non-English12821245
LMArena Chinese12891263
LMArena Russian12861227
LMArena French1317—
LMArena German1287—
LMArena Japanese1244—
LMArena Korean1237—
LMArena Spanish1281—

Instruction Following Too close to call

Grok-2 (Dec 2024): 67.1 (#197), Llama 3.1 Nemotron 70b Instruct: 66.2 (#208)

BenchmarkGrok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
LMArena Instruction Following12701252
LiveBench Instruction Following69.6%—

Long Context Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 38.7 (#186), Llama 3.1 Nemotron 70b Instruct: 37.5 (#210)

BenchmarkGrok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
LMArena Longer Query12761239

Writing & Preference Too close to call

Grok-2 (Dec 2024): 48.8 (#192), Llama 3.1 Nemotron 70b Instruct: 48.6 (#197)

BenchmarkGrok-2 (Dec 2024)Llama 3.1 Nemotron 70b Instruct
LMArena Text13051283
LMArena Creative Writing12841269
LMArena Multi-Turn12901275
Short-Story Creative Writing63.6%—
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Llama 3.1 Nemotron 70b Instruct?

Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.0 to 33.4 on the Noometry Index.

Is Grok-2 (Dec 2024) or Llama 3.1 Nemotron 70b Instruct better for coding?

Llama 3.1 Nemotron 70b Instruct scores higher on coding benchmarks: 35.3 versus 32.9 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Llama 3.1 Nemotron 70b Instruct share?

12 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Llama 3.1 Nemotron 70b Instruct has 14.

Related comparisons

Go deeper