GLM-4.5 vs GPT-OSS 20B

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

Quick Verdict

GLM-4.5 wins overall with a score of 28 vs 22 (6 point difference).GLM-4.5 wins 4 out of 4 categories.

Knowledge

GLM-4.5

GLM-4.5

34.8

GPT-OSS 20B

28.8

37
MMLU
31
36
GPQA
30
34
SuperGPQA
28
32
OpenBookQA
26

Coding

GLM-4.5

GLM-4.5

29

GPT-OSS 20B

23

29
HumanEval
23

Mathematics

GLM-4.5

GLM-4.5

36

GPT-OSS 20B

30

37
AIME 2023
31
39
AIME 2024
33
38
AIME 2025
32
33
HMMT Feb 2023
27
35
HMMT Feb 2024
29
34
HMMT Feb 2025
28
36
BRUMO 2025
30

Reasoning

GLM-4.5

GLM-4.5

34

GPT-OSS 20B

28

35
SimpleQA
29
33
MuSR
27

Frequently Asked Questions

Which is better, GLM-4.5 or GPT-OSS 20B?

GLM-4.5 scores higher overall with 28 vs 22, a difference of 6 points across all benchmarks.

Which is better for knowledge tasks, GLM-4.5 or GPT-OSS 20B?

GLM-4.5 leads in knowledge tasks with an average score of 34.8 vs 28.8.

Which is better for coding, GLM-4.5 or GPT-OSS 20B?

GLM-4.5 leads in coding with an average score of 29 vs 23.

Which is better for math, GLM-4.5 or GPT-OSS 20B?

GLM-4.5 leads in math with an average score of 36 vs 30.

Which is better for reasoning, GLM-4.5 or GPT-OSS 20B?

GLM-4.5 leads in reasoning with an average score of 34 vs 28.