Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GLM-4.5-Air wins overall with a score of 26 vs 22 (4 point difference).GLM-4.5-Air wins 4 out of 4 categories.
GLM-4.5-Air
32.8
GPT-OSS 20B
28.8
GLM-4.5-Air
27
GPT-OSS 20B
23
GLM-4.5-Air
34
GPT-OSS 20B
30
GLM-4.5-Air
32
GPT-OSS 20B
28
GLM-4.5-Air scores higher overall with 26 vs 22, a difference of 4 points across all benchmarks.
GLM-4.5-Air leads in knowledge tasks with an average score of 32.8 vs 28.8.
GLM-4.5-Air leads in coding with an average score of 27 vs 23.
GLM-4.5-Air leads in math with an average score of 34 vs 30.
GLM-4.5-Air leads in reasoning with an average score of 32 vs 28.