GPT-OSS 20B vs Mistral Large 2

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

Quick Verdict

Mistral Large 2 wins overall with a score of 57 vs 22 (35 point difference).Mistral Large 2 wins 4 out of 4 categories.

Knowledge

Mistral Large 2

GPT-OSS 20B

28.8

Mistral Large 2

66.5

31
MMLU
68
30
GPQA
68
28
SuperGPQA
66
26
OpenBookQA
64

Coding

Mistral Large 2

GPT-OSS 20B

23

Mistral Large 2

60

23
HumanEval
60

Mathematics

Mistral Large 2

GPT-OSS 20B

30

Mistral Large 2

67

31
AIME 2023
68
33
AIME 2024
70
32
AIME 2025
69
27
HMMT Feb 2023
64
29
HMMT Feb 2024
66
28
HMMT Feb 2025
65
30
BRUMO 2025
67

Reasoning

Mistral Large 2

GPT-OSS 20B

28

Mistral Large 2

65

29
SimpleQA
66
27
MuSR
64

Frequently Asked Questions

Which is better, GPT-OSS 20B or Mistral Large 2?

Mistral Large 2 scores higher overall with 57 vs 22, a difference of 35 points across all benchmarks.

Which is better for knowledge tasks, GPT-OSS 20B or Mistral Large 2?

Mistral Large 2 leads in knowledge tasks with an average score of 66.5 vs 28.8.

Which is better for coding, GPT-OSS 20B or Mistral Large 2?

Mistral Large 2 leads in coding with an average score of 60 vs 23.

Which is better for math, GPT-OSS 20B or Mistral Large 2?

Mistral Large 2 leads in math with an average score of 67 vs 30.

Which is better for reasoning, GPT-OSS 20B or Mistral Large 2?

Mistral Large 2 leads in reasoning with an average score of 65 vs 28.