Noometry

Model comparison

Grok-2 (Dec 2024) vs Nemotron 3 Ultra

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.7 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 29.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 86.7% for Nemotron 3 Ultra.
  • Nemotron 3 Ultra has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Nemotron 3 Ultra
ProviderxAINVIDIA
Noometry Index33.742.5
Released2024-08-132026-06-04
WeightsProprietaryOpen
Context window—262K
Max output—128K
Input $ / M tokens—$0.50
Output $ / M tokens—$2.20
Results tracked3430

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

Category by category

Coding Nemotron 3 Ultra leads

Grok-2 (Dec 2024): 33.3 (#258), Nemotron 3 Ultra: 38.1 (#182)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
WeirdML22.2%43.5%
LMArena Coding12871468
FrontierCode—13.6%
SciCode—40.3%
LiveBench Coding46.4%—

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Nemotron 3 Ultra: 23.4 (#126)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
APEX-Agents—22.7%

Reasoning Nemotron 3 Ultra leads

Grok-2 (Dec 2024): 16.9 (#299), Nemotron 3 Ultra: 31.0 (#82)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
LMArena Hard Prompts12721452
DTBench65.2%90.1%
Epoch Capabilities Index130.48146.17
SimpleBench22.7%—
CritPt—3.1%
Chess Puzzles—12%
LiveBench Reasoning54.8%—
Mystery Game Puzzles—20%
LiveBench Data Analysis54.5%—
LMCA—36.9%
LiveBench54.3%—

Math Nemotron 3 Ultra leads

Grok-2 (Dec 2024): 20.8 (#284), Nemotron 3 Ultra: 35.3 (#187)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
OTIS Mock AIME 2024-202511.5%86.7%
LMArena Math12831457
ProofBench—2%
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Nemotron 3 Ultra leads

Grok-2 (Dec 2024): 29.8 (#233), Nemotron 3 Ultra: 52.5 (#61)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
GPQA Diamond53.8%85.4%
LMArena Expert12541472
Confabulations20.1%—

Multilingual Nemotron 3 Ultra leads

Grok-2 (Dec 2024): 43.1 (#188), Nemotron 3 Ultra: 53.5 (#64)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
LMArena Non-English12821427
LMArena Chinese12891497
LMArena French13181472
LMArena German12871471
LMArena Korean12371386
LMArena Russian12861417
LMArena Spanish12811454
LMArena Japanese1244—

Instruction Following Nemotron 3 Ultra leads

Grok-2 (Dec 2024): 66.9 (#202), Nemotron 3 Ultra: 74.7 (#88)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
LMArena Instruction Following12701418
LiveBench Instruction Following69.6%—

Long Context Nemotron 3 Ultra leads

Grok-2 (Dec 2024): 38.8 (#190), Nemotron 3 Ultra: 43.9 (#81)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
LMArena Longer Query12761437

Writing & Preference Nemotron 3 Ultra leads

Grok-2 (Dec 2024): 48.6 (#198), Nemotron 3 Ultra: 66.3 (#36)

BenchmarkGrok-2 (Dec 2024)Nemotron 3 Ultra
LMArena Text13051445
LMArena Creative Writing12841398
LMArena Multi-Turn12901411
Short-Story Creative Writing63.6%—
EQ-Bench Creative Writing—1692
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.7 on the Noometry Index.

Is Grok-2 (Dec 2024) or Nemotron 3 Ultra better for coding?

Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 33.3 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Nemotron 3 Ultra share?

21 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Nemotron 3 Ultra has 30.

Related comparisons

Go deeper