GLM-4.5 vs Ministral 3 8B

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

GLM-4.5 is clearly ahead on the aggregate, 36 to 32. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GLM-4.5's sharpest advantage is in multimodal & grounded, where it averages 41 against 32.4. The single biggest benchmark swing on the page is MRCRv2, 52 to 41. Ministral 3 8B does hit back in multilingual, so the answer changes if that is the part of the workload you care about most.

Quick Verdict

Pick GLM-4.5 if you want the stronger benchmark profile. Ministral 3 8B only becomes the better choice if multilingual is the priority.

Agentic

GLM-4.5

GLM-4.5

31.3

Ministral 3 8B

28.9

28
Terminal-Bench 2.0
26
37
BrowseComp
36
31
OSWorld-Verified
27

Coding

GLM-4.5

GLM-4.5

14.4

Ministral 3 8B

14.2

29
HumanEval
23
18
SWE-bench Verified
16
13
LiveCodeBench
15
15
SWE-bench Pro
13

Multimodal & Grounded

GLM-4.5

GLM-4.5

41

Ministral 3 8B

32.4

36
MMMU-Pro
27
47
OfficeQA Pro
39

Reasoning

GLM-4.5

GLM-4.5

43.8

Ministral 3 8B

36.1

35
SimpleQA
28
33
MuSR
26
61
BBH
63
48
LongBench v2
38
52
MRCRv2
41

Knowledge

GLM-4.5

GLM-4.5

32

Ministral 3 8B

28

37
MMLU
28
36
GPQA
27
34
SuperGPQA
25
32
OpenBookQA
23
51
MMLU-Pro
52
3
HLE
3
40
FrontierScience
32

Instruction Following

Ministral 3 8B

GLM-4.5

68

Ministral 3 8B

69

68
IFEval
69

Multilingual

Ministral 3 8B

GLM-4.5

58.1

Ministral 3 8B

61.7

60
MGSM
63
57
MMLU-ProX
61

Mathematics

GLM-4.5

GLM-4.5

45.5

Ministral 3 8B

43.3

37
AIME 2023
30
39
AIME 2024
32
38
AIME 2025
33
33
HMMT Feb 2023
26
35
HMMT Feb 2024
28
34
HMMT Feb 2025
27
36
BRUMO 2025
29
57
MATH-500
60

Frequently Asked Questions

Which is better, GLM-4.5 or Ministral 3 8B?

GLM-4.5 is ahead overall, 36 to 32. The biggest single separator in this matchup is MRCRv2, where the scores are 52 and 41.

Which is better for knowledge tasks, GLM-4.5 or Ministral 3 8B?

GLM-4.5 has the edge for knowledge tasks in this comparison, averaging 32 versus 28. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-4.5 or Ministral 3 8B?

GLM-4.5 has the edge for coding in this comparison, averaging 14.4 versus 14.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, GLM-4.5 or Ministral 3 8B?

GLM-4.5 has the edge for math in this comparison, averaging 45.5 versus 43.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GLM-4.5 or Ministral 3 8B?

GLM-4.5 has the edge for reasoning in this comparison, averaging 43.8 versus 36.1. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GLM-4.5 or Ministral 3 8B?

GLM-4.5 has the edge for agentic tasks in this comparison, averaging 31.3 versus 28.9. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GLM-4.5 or Ministral 3 8B?

GLM-4.5 has the edge for multimodal and grounded tasks in this comparison, averaging 41 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GLM-4.5 or Ministral 3 8B?

Ministral 3 8B has the edge for instruction following in this comparison, averaging 69 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GLM-4.5 or Ministral 3 8B?

Ministral 3 8B has the edge for multilingual tasks in this comparison, averaging 61.7 versus 58.1. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.

Last updated: March 12, 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.