GPT-4o mini vs GLM-4.5

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

GPT-4o mini is clearly ahead on the aggregate, 43 to 38. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-4o mini's sharpest advantage is in coding, where it averages 87.2 against 20. The single biggest benchmark swing on the page is HumanEval, 87.2 to 29.

Quick Verdict

Pick GPT-4o mini if you want the stronger benchmark profile. GLM-4.5 only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Knowledge

GPT-4o mini

GPT-4o mini

82

GLM-4.5

32.2

82
MMLU
37
-
GPQA
36
-
SuperGPQA
34
-
OpenBookQA
32
-
MMLU-Pro
51
-
HLE
3

Coding

GPT-4o mini

GPT-4o mini

87.2

GLM-4.5

20

87.2
HumanEval
29
-
SWE-bench Verified
18
-
LiveCodeBench
13

Mathematics

GLM-4.5
-
AIME 2023
37
-
AIME 2024
39
-
AIME 2025
38
-
HMMT Feb 2023
33
-
HMMT Feb 2024
35
-
HMMT Feb 2025
34
-
BRUMO 2025
36
-
MATH-500
57

Reasoning

GLM-4.5
-
SimpleQA
35
-
MuSR
33
-
BBH
61

Instruction Following

GLM-4.5
-
IFEval
68

Multilingual

GPT-4o mini

GPT-4o mini

87

GLM-4.5

60

87
MGSM
60

Frequently Asked Questions

Which is better, GPT-4o mini or GLM-4.5?

GPT-4o mini is ahead overall, 43 to 38. The biggest single separator in this matchup is HumanEval, where the scores are 87.2 and 29.

Which is better for knowledge tasks, GPT-4o mini or GLM-4.5?

GPT-4o mini has the edge for knowledge tasks in this comparison, averaging 82 versus 32.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-4o mini or GLM-4.5?

GPT-4o mini has the edge for coding in this comparison, averaging 87.2 versus 20. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-4o mini or GLM-4.5?

GPT-4o mini has the edge for multilingual tasks in this comparison, averaging 87 versus 60. Inside this category, MGSM is the benchmark that creates the most daylight between them.

Last updated: March 9, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.