benchlm.ai

GPT-5.1-Codex-Max vs Llama 3.1 405B

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

Quick Verdict

GPT-5.1-Codex-Max wins overall with a score of 77 vs 58 (19 point difference).GPT-5.1-Codex-Max wins 4 out of 4 categories.

GPT-5.1-Codex-Max

CreatorOpenAI
TypeProprietary
Context400K
Score77

Llama 3.1 405B

CreatorMeta
TypeOpen Weight
Context128K
Score58

Knowledge

GPT-5.1-Codex-Max

GPT-5.1-Codex-Max

95

Llama 3.1 405B

68.5

98
MMLU
70
96
GPQA
70
94
SuperGPQA
68
92
OpenBookQA
66

Coding

GPT-5.1-Codex-Max

GPT-5.1-Codex-Max

94

Llama 3.1 405B

62

94
HumanEval
62

Mathematics

GPT-5.1-Codex-Max

GPT-5.1-Codex-Max

97.1

Llama 3.1 405B

69

99
AIME 2023
70
99
AIME 2024
72
98
AIME 2025
71
95
HMMT Feb 2023
66
97
HMMT Feb 2024
68
96
HMMT Feb 2025
67
96
BRUMO 2025
69

Reasoning

GPT-5.1-Codex-Max

GPT-5.1-Codex-Max

93

Llama 3.1 405B

67

94
SimpleQA
68
92
MuSR
66

Frequently Asked Questions

Which is better, GPT-5.1-Codex-Max or Llama 3.1 405B?

GPT-5.1-Codex-Max scores higher overall with 77 vs 58, a difference of 19 points across all benchmarks.

Which is better for knowledge tasks, GPT-5.1-Codex-Max or Llama 3.1 405B?

GPT-5.1-Codex-Max leads in knowledge tasks with an average score of 95 vs 68.5.

Which is better for coding, GPT-5.1-Codex-Max or Llama 3.1 405B?

GPT-5.1-Codex-Max leads in coding with an average score of 94 vs 62.

Which is better for math, GPT-5.1-Codex-Max or Llama 3.1 405B?

GPT-5.1-Codex-Max leads in math with an average score of 97.1 vs 69.

Which is better for reasoning, GPT-5.1-Codex-Max or Llama 3.1 405B?

GPT-5.1-Codex-Max leads in reasoning with an average score of 93 vs 67.

Related Comparisons

GPT-5.1-Codex-Max vs GPT-5.4GPT-5.1-Codex-Max vs Gemini 3.1 ProGPT-5.1-Codex-Max vs Claude Opus 4.6GPT-5.1-Codex-Max vs GPT-5.3 CodexGPT-5.1-Codex-Max vs Grok 4.1GPT-5.1-Codex-Max vs GPT-5.2