Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GLM-4.7 is clearly ahead on the aggregate, 67 to 55. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GLM-4.7's sharpest advantage is in agentic, where it averages 66.1 against 48.4. The single biggest benchmark swing on the page is HumanEval, 78 to 58.
GLM-4.7 is the reasoning model in the pair, while Ministral 3 14B 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. GLM-4.7 gives you the larger context window at 200K, compared with 128K for Ministral 3 14B.
Pick GLM-4.7 if you want the stronger benchmark profile. Ministral 3 14B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
GLM-4.7
66.1
Ministral 3 14B
48.4
GLM-4.7
46.6
Ministral 3 14B
33
GLM-4.7
70.5
Ministral 3 14B
70.5
GLM-4.7
80.2
Ministral 3 14B
63.6
GLM-4.7
61.8
Ministral 3 14B
50.1
GLM-4.7
85
Ministral 3 14B
80
GLM-4.7
79.1
Ministral 3 14B
76.8
GLM-4.7
85
Ministral 3 14B
69.7
GLM-4.7 is ahead overall, 67 to 55. The biggest single separator in this matchup is HumanEval, where the scores are 78 and 58.
GLM-4.7 has the edge for knowledge tasks in this comparison, averaging 61.8 versus 50.1. Inside this category, MMLU is the benchmark that creates the most daylight between them.
GLM-4.7 has the edge for coding in this comparison, averaging 46.6 versus 33. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
GLM-4.7 has the edge for math in this comparison, averaging 85 versus 69.7. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
GLM-4.7 has the edge for reasoning in this comparison, averaging 80.2 versus 63.6. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
GLM-4.7 has the edge for agentic tasks in this comparison, averaging 66.1 versus 48.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
GLM-4.7 and Ministral 3 14B are effectively tied for multimodal and grounded tasks here, both landing at 70.5 on average.
GLM-4.7 has the edge for instruction following in this comparison, averaging 85 versus 80. Inside this category, IFEval is the benchmark that creates the most daylight between them.
GLM-4.7 has the edge for multilingual tasks in this comparison, averaging 79.1 versus 76.8. Inside this category, MMLU-ProX 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.