Noometry

Model comparison

Grok-3 mini vs Nemotron 3 Ultra

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 41.2 on the Noometry Index.

Last verified . 20 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Grok-3 mini scores higher in 3 categories and Nemotron 3 Ultra in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Nemotron 3 Ultra leads 31.0 to 13.6.
  • The biggest single-benchmark swing is GPQA Diamond: 76.3% for Grok-3 mini and 85.4% for Nemotron 3 Ultra.
  • Nemotron 3 Ultra has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniNemotron 3 Ultra
ProviderxAINVIDIA
Noometry Index41.242.5
Released2025-04-092026-06-04
WeightsProprietaryOpen
Context window—262K
Max output—128K
Input $ / M tokens—$0.60
Output $ / M tokens—$2.40
Results tracked3530

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

Category by category

Coding Grok-3 mini leads

Grok-3 mini: 40.8 (#131), Nemotron 3 Ultra: 38.1 (#182)

BenchmarkGrok-3 miniNemotron 3 Ultra
WeirdML42.6%43.5%
LMArena Coding13791468
FrontierCode—13.6%
Aider Polyglot49.3%—
SciCode—40.3%

Agentic & Tool Use Not comparable

Grok-3 mini: —, Nemotron 3 Ultra: 23.4 (#126)

BenchmarkGrok-3 miniNemotron 3 Ultra
APEX-Agents—22.7%

Reasoning Nemotron 3 Ultra leads

Grok-3 mini: 13.6 (#334), Nemotron 3 Ultra: 31.0 (#82)

BenchmarkGrok-3 miniNemotron 3 Ultra
LMArena Hard Prompts13751452
Epoch Capabilities Index140.35146.17
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
CritPt—3.1%
Chess Puzzles—12%
Mystery Game Puzzles—20%
DTBench—90.1%
LMCA—36.9%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Nemotron 3 Ultra: 35.3 (#187)

BenchmarkGrok-3 miniNemotron 3 Ultra
OTIS Mock AIME 2024-202577.8%86.7%
LMArena Math13861457
ProofBench—2%
Omni-MATH31.8%—
MATH Level 590.9%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Nemotron 3 Ultra leads

Grok-3 mini: 46.4 (#81), Nemotron 3 Ultra: 52.5 (#61)

BenchmarkGrok-3 miniNemotron 3 Ultra
GPQA Diamond76.3%85.4%
LMArena Expert13951472
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—

Multilingual Nemotron 3 Ultra leads

Grok-3 mini: 48.1 (#145), Nemotron 3 Ultra: 53.5 (#64)

BenchmarkGrok-3 miniNemotron 3 Ultra
LMArena Non-English13521427
LMArena Chinese13871497
LMArena French13571472
LMArena German13491471
LMArena Korean13351386
LMArena Russian13531417
LMArena Spanish13811454
LMArena Japanese1342—

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Nemotron 3 Ultra: 74.7 (#88)

BenchmarkGrok-3 miniNemotron 3 Ultra
LMArena Instruction Following13571418
IFEval95.1%—

Long Context Nemotron 3 Ultra leads

Grok-3 mini: 41.0 (#147), Nemotron 3 Ultra: 43.9 (#81)

BenchmarkGrok-3 miniNemotron 3 Ultra
LMArena Longer Query13721437
Fiction.LiveBench66.7%—

Writing & Preference Nemotron 3 Ultra leads

Grok-3 mini: 52.5 (#169), Nemotron 3 Ultra: 66.3 (#36)

BenchmarkGrok-3 miniNemotron 3 Ultra
LMArena Text13701445
LMArena Creative Writing13421398
LMArena Multi-Turn13551411
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing—1692
WildBench65.1%—

Frequently asked questions

Is Grok-3 mini better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 41.2 on the Noometry Index.

Is Grok-3 mini or Nemotron 3 Ultra better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 38.1 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Nemotron 3 Ultra share?

20 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Nemotron 3 Ultra has 30.

Related comparisons

Go deeper