benchlm.ai

GLM-4.7-Flash vs GPT-OSS 20B

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

Quick Verdict

GLM-4.7-Flash wins overall with a score of 56 vs 22 (34 point difference).GLM-4.7-Flash wins 4 out of 4 categories.

GLM-4.7-Flash

CreatorZhipu AI
TypeOpen Weight
Context200K
Score56

GPT-OSS 20B

CreatorOpenAI
TypeOpen Weight
Context128K
Score22

Knowledge

GLM-4.7-Flash

GLM-4.7-Flash

63.8

GPT-OSS 20B

28.8

66
MMLU
31
65
GPQA
30
63
SuperGPQA
28
61
OpenBookQA
26

Coding

GLM-4.7-Flash

GLM-4.7-Flash

58

GPT-OSS 20B

23

58
HumanEval
23

Mathematics

GLM-4.7-Flash

GLM-4.7-Flash

65

GPT-OSS 20B

30

66
AIME 2023
31
68
AIME 2024
33
67
AIME 2025
32
62
HMMT Feb 2023
27
64
HMMT Feb 2024
29
63
HMMT Feb 2025
28
65
BRUMO 2025
30

Reasoning

GLM-4.7-Flash

GLM-4.7-Flash

62

GPT-OSS 20B

28

63
SimpleQA
29
61
MuSR
27

Frequently Asked Questions

Which is better, GLM-4.7-Flash or GPT-OSS 20B?

GLM-4.7-Flash scores higher overall with 56 vs 22, a difference of 34 points across all benchmarks.

Which is better for knowledge tasks, GLM-4.7-Flash or GPT-OSS 20B?

GLM-4.7-Flash leads in knowledge tasks with an average score of 63.8 vs 28.8.

Which is better for coding, GLM-4.7-Flash or GPT-OSS 20B?

GLM-4.7-Flash leads in coding with an average score of 58 vs 23.

Which is better for math, GLM-4.7-Flash or GPT-OSS 20B?

GLM-4.7-Flash leads in math with an average score of 65 vs 30.

Which is better for reasoning, GLM-4.7-Flash or GPT-OSS 20B?

GLM-4.7-Flash leads in reasoning with an average score of 62 vs 28.

Related Comparisons

GLM-4.7-Flash vs GPT-5.4GLM-4.7-Flash vs Gemini 3.1 ProGLM-4.7-Flash vs Claude Opus 4.6GLM-4.7-Flash vs GPT-5.3 CodexGLM-4.7-Flash vs Grok 4.1GLM-4.7-Flash vs GPT-5.2