benchlm.ai

Nemotron 3 Ultra 500B vs Nemotron-4 15B

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

Nemotron 3 Ultra 500B wins overall with a score of 60 vs 45 (15 point difference).Nemotron 3 Ultra 500B wins 4 out of 4 categories.

Nemotron 3 Ultra 500B

CreatorNVIDIA
TypeOpen Weight
Context32K
Score60

Nemotron-4 15B

CreatorNVIDIA
TypeOpen Weight
Context32K
Score45

Knowledge

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

71.8

Nemotron-4 15B

51.8

74
MMLU
54
73
GPQA
53
71
SuperGPQA
51
69
OpenBookQA
49

Coding

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

66

Nemotron-4 15B

46

66
HumanEval
46

Mathematics

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

73

Nemotron-4 15B

53

74
AIME 2023
54
76
AIME 2024
56
75
AIME 2025
55
70
HMMT Feb 2023
50
72
HMMT Feb 2024
52
71
HMMT Feb 2025
51
73
BRUMO 2025
53

Reasoning

Nemotron 3 Ultra 500B

Nemotron 3 Ultra 500B

70

Nemotron-4 15B

51

71
SimpleQA
52
69
MuSR
50

Frequently Asked Questions

Which is better, Nemotron 3 Ultra 500B or Nemotron-4 15B?

Nemotron 3 Ultra 500B scores higher overall with 60 vs 45, a difference of 15 points across all benchmarks.

Which is better for knowledge tasks, Nemotron 3 Ultra 500B or Nemotron-4 15B?

Nemotron 3 Ultra 500B leads in knowledge tasks with an average score of 71.8 vs 51.8.

Which is better for coding, Nemotron 3 Ultra 500B or Nemotron-4 15B?

Nemotron 3 Ultra 500B leads in coding with an average score of 66 vs 46.

Which is better for math, Nemotron 3 Ultra 500B or Nemotron-4 15B?

Nemotron 3 Ultra 500B leads in math with an average score of 73 vs 53.

Which is better for reasoning, Nemotron 3 Ultra 500B or Nemotron-4 15B?

Nemotron 3 Ultra 500B leads in reasoning with an average score of 70 vs 51.

Related Comparisons

Nemotron 3 Ultra 500B vs GPT-5.4Nemotron 3 Ultra 500B vs Gemini 3.1 ProNemotron 3 Ultra 500B vs Claude Opus 4.6Nemotron 3 Ultra 500B vs GPT-5.3 CodexNemotron 3 Ultra 500B vs Grok 4.1Nemotron 3 Ultra 500B vs GPT-5.2