GPT-OSS 120B vs Llama 4 Scout

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

Quick Verdict

GPT-OSS 120B wins overall with a score of 42 vs 38 (4 point difference).GPT-OSS 120B wins 4 out of 4 categories.

Knowledge

GPT-OSS 120B

GPT-OSS 120B

48.8

Llama 4 Scout

44.8

51
MMLU
47
50
GPQA
46
48
SuperGPQA
44
46
OpenBookQA
42

Coding

GPT-OSS 120B

GPT-OSS 120B

43

Llama 4 Scout

39

43
HumanEval
39

Mathematics

GPT-OSS 120B

GPT-OSS 120B

50

Llama 4 Scout

46

51
AIME 2023
47
53
AIME 2024
49
52
AIME 2025
48
47
HMMT Feb 2023
43
49
HMMT Feb 2024
45
48
HMMT Feb 2025
44
50
BRUMO 2025
46

Reasoning

GPT-OSS 120B

GPT-OSS 120B

48

Llama 4 Scout

44

49
SimpleQA
45
47
MuSR
43

Frequently Asked Questions

Which is better, GPT-OSS 120B or Llama 4 Scout?

GPT-OSS 120B scores higher overall with 42 vs 38, a difference of 4 points across all benchmarks.

Which is better for knowledge tasks, GPT-OSS 120B or Llama 4 Scout?

GPT-OSS 120B leads in knowledge tasks with an average score of 48.8 vs 44.8.

Which is better for coding, GPT-OSS 120B or Llama 4 Scout?

GPT-OSS 120B leads in coding with an average score of 43 vs 39.

Which is better for math, GPT-OSS 120B or Llama 4 Scout?

GPT-OSS 120B leads in math with an average score of 50 vs 46.

Which is better for reasoning, GPT-OSS 120B or Llama 4 Scout?

GPT-OSS 120B leads in reasoning with an average score of 48 vs 44.