Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GLM-4.5-Air is clearly ahead on the aggregate, 35 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GLM-4.5-Air's sharpest advantage is in multimodal & grounded, where it averages 39.6 against 30.4. The single biggest benchmark swing on the page is HumanEval, 27 to 16. Ministral 3 3B (Reasoning) does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Ministral 3 3B (Reasoning) is the reasoning model in the pair, while GLM-4.5-Air is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.
Pick GLM-4.5-Air if you want the stronger benchmark profile. Ministral 3 3B (Reasoning) only becomes the better choice if agentic is the priority or you want the stronger reasoning-first profile.
GLM-4.5-Air
30.3
Ministral 3 3B (Reasoning)
34
GLM-4.5-Air
14.6
Ministral 3 3B (Reasoning)
7.2
GLM-4.5-Air
39.6
Ministral 3 3B (Reasoning)
30.4
GLM-4.5-Air
42.6
Ministral 3 3B (Reasoning)
35.3
GLM-4.5-Air
31.1
Ministral 3 3B (Reasoning)
25.2
GLM-4.5-Air
68
Ministral 3 3B (Reasoning)
68
GLM-4.5-Air
59.1
Ministral 3 3B (Reasoning)
59.7
GLM-4.5-Air
44.4
Ministral 3 3B (Reasoning)
40.9
GLM-4.5-Air is ahead overall, 35 to 31. The biggest single separator in this matchup is HumanEval, where the scores are 27 and 16.
GLM-4.5-Air has the edge for knowledge tasks in this comparison, averaging 31.1 versus 25.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.
GLM-4.5-Air has the edge for coding in this comparison, averaging 14.6 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
GLM-4.5-Air has the edge for math in this comparison, averaging 44.4 versus 40.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
GLM-4.5-Air has the edge for reasoning in this comparison, averaging 42.6 versus 35.3. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
Ministral 3 3B (Reasoning) has the edge for agentic tasks in this comparison, averaging 34 versus 30.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
GLM-4.5-Air has the edge for multimodal and grounded tasks in this comparison, averaging 39.6 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
GLM-4.5-Air and Ministral 3 3B (Reasoning) are effectively tied for instruction following here, both landing at 68 on average.
Ministral 3 3B (Reasoning) has the edge for multilingual tasks in this comparison, averaging 59.7 versus 59.1. Inside this category, MGSM is the benchmark that creates the most daylight between them.
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.