benchlm.ai

GPT-5.2-Codex vs Nemotron Ultra 253B

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

Quick Verdict

GPT-5.2-Codex wins overall with a score of 82 vs 40 (42 point difference).GPT-5.2-Codex wins 4 out of 4 categories.

GPT-5.2-Codex

CreatorOpenAI
TypeProprietary
Context400K
Score82

Nemotron Ultra 253B

CreatorNVIDIA
TypeOpen Weight
Context32K
Score40

Knowledge

GPT-5.2-Codex

GPT-5.2-Codex

96

Nemotron Ultra 253B

46.8

99
MMLU
49
97
GPQA
48
95
SuperGPQA
46
93
OpenBookQA
44

Coding

GPT-5.2-Codex

GPT-5.2-Codex

95

Nemotron Ultra 253B

41

95
HumanEval
41

Mathematics

GPT-5.2-Codex

GPT-5.2-Codex

97.1

Nemotron Ultra 253B

48

99
AIME 2023
49
99
AIME 2024
51
98
AIME 2025
50
95
HMMT Feb 2023
45
97
HMMT Feb 2024
47
96
HMMT Feb 2025
46
96
BRUMO 2025
48

Reasoning

GPT-5.2-Codex

GPT-5.2-Codex

94

Nemotron Ultra 253B

46

95
SimpleQA
47
93
MuSR
45

Frequently Asked Questions

Which is better, GPT-5.2-Codex or Nemotron Ultra 253B?

GPT-5.2-Codex scores higher overall with 82 vs 40, a difference of 42 points across all benchmarks.

Which is better for knowledge tasks, GPT-5.2-Codex or Nemotron Ultra 253B?

GPT-5.2-Codex leads in knowledge tasks with an average score of 96 vs 46.8.

Which is better for coding, GPT-5.2-Codex or Nemotron Ultra 253B?

GPT-5.2-Codex leads in coding with an average score of 95 vs 41.

Which is better for math, GPT-5.2-Codex or Nemotron Ultra 253B?

GPT-5.2-Codex leads in math with an average score of 97.1 vs 48.

Which is better for reasoning, GPT-5.2-Codex or Nemotron Ultra 253B?

GPT-5.2-Codex leads in reasoning with an average score of 94 vs 46.

Related Comparisons

GPT-5.2-Codex vs GPT-5.4GPT-5.2-Codex vs Gemini 3.1 ProGPT-5.2-Codex vs Claude Opus 4.6GPT-5.2-Codex vs GPT-5.3 CodexGPT-5.2-Codex vs Grok 4.1GPT-5.2-Codex vs GPT-5.2