GPT-OSS 20B vs Mistral Large 3

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

Quick Verdict

Mistral Large 3 wins overall with a score of 61 vs 22 (39 point difference).Mistral Large 3 wins 4 out of 4 categories.

Knowledge

Mistral Large 3

GPT-OSS 20B

28.8

Mistral Large 3

73.8

31
MMLU
76
30
GPQA
75
28
SuperGPQA
73
26
OpenBookQA
71

Coding

Mistral Large 3

GPT-OSS 20B

23

Mistral Large 3

68

23
HumanEval
68

Mathematics

Mistral Large 3

GPT-OSS 20B

30

Mistral Large 3

75

31
AIME 2023
76
33
AIME 2024
78
32
AIME 2025
77
27
HMMT Feb 2023
72
29
HMMT Feb 2024
74
28
HMMT Feb 2025
73
30
BRUMO 2025
75

Reasoning

Mistral Large 3

GPT-OSS 20B

28

Mistral Large 3

72

29
SimpleQA
73
27
MuSR
71

Frequently Asked Questions

Which is better, GPT-OSS 20B or Mistral Large 3?

Mistral Large 3 scores higher overall with 61 vs 22, a difference of 39 points across all benchmarks.

Which is better for knowledge tasks, GPT-OSS 20B or Mistral Large 3?

Mistral Large 3 leads in knowledge tasks with an average score of 73.8 vs 28.8.

Which is better for coding, GPT-OSS 20B or Mistral Large 3?

Mistral Large 3 leads in coding with an average score of 68 vs 23.

Which is better for math, GPT-OSS 20B or Mistral Large 3?

Mistral Large 3 leads in math with an average score of 75 vs 30.

Which is better for reasoning, GPT-OSS 20B or Mistral Large 3?

Mistral Large 3 leads in reasoning with an average score of 72 vs 28.