Nemotron Ultra 253B vs Z-1

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

Quick Verdict

Z-1 wins overall with a score of 43 vs 40 (3 point difference).Z-1 wins 4 out of 4 categories.

Knowledge

Z-1

Nemotron Ultra 253B

46.8

Z-1

49.8

49
MMLU
52
48
GPQA
51
46
SuperGPQA
49
44
OpenBookQA
47

Coding

Z-1

Nemotron Ultra 253B

41

Z-1

44

41
HumanEval
44

Mathematics

Z-1

Nemotron Ultra 253B

48

Z-1

51

49
AIME 2023
52
51
AIME 2024
54
50
AIME 2025
53
45
HMMT Feb 2023
48
47
HMMT Feb 2024
50
46
HMMT Feb 2025
49
48
BRUMO 2025
51

Reasoning

Z-1

Nemotron Ultra 253B

46

Z-1

49

47
SimpleQA
50
45
MuSR
48

Frequently Asked Questions

Which is better, Nemotron Ultra 253B or Z-1?

Z-1 scores higher overall with 43 vs 40, a difference of 3 points across all benchmarks.

Which is better for knowledge tasks, Nemotron Ultra 253B or Z-1?

Z-1 leads in knowledge tasks with an average score of 49.8 vs 46.8.

Which is better for coding, Nemotron Ultra 253B or Z-1?

Z-1 leads in coding with an average score of 44 vs 41.

Which is better for math, Nemotron Ultra 253B or Z-1?

Z-1 leads in math with an average score of 51 vs 48.

Which is better for reasoning, Nemotron Ultra 253B or Z-1?

Z-1 leads in reasoning with an average score of 49 vs 46.