Ministral 3 14B (Reasoning) vs Qwen2.5-VL-32B

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

Ministral 3 14B (Reasoning) is clearly ahead on the aggregate, 60 to 38. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Ministral 3 14B (Reasoning)'s sharpest advantage is in reasoning, where it averages 69.2 against 43.2. The single biggest benchmark swing on the page is MuSR, 70 to 39.

Ministral 3 14B (Reasoning) is the reasoning model in the pair, while Qwen2.5-VL-32B 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. Ministral 3 14B (Reasoning) gives you the larger context window at 128K, compared with 32K for Qwen2.5-VL-32B.

Quick Verdict

Pick Ministral 3 14B (Reasoning) if you want the stronger benchmark profile. Qwen2.5-VL-32B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

58.5

Qwen2.5-VL-32B

33.5

60
Terminal-Bench 2.0
30
61
BrowseComp
41
55
OSWorld-Verified
32

Coding

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

35

Qwen2.5-VL-32B

14.3

62
HumanEval
35
39
SWE-bench Verified
17
33
LiveCodeBench
11
36
SWE-bench Pro
17

Multimodal & Grounded

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

71.5

Qwen2.5-VL-32B

52.2

71
MMMU-Pro
58
72
OfficeQA Pro
45

Reasoning

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

69.2

Qwen2.5-VL-32B

43.2

70
SimpleQA
41
70
MuSR
39
80
BBH
61
66
LongBench v2
42
66
MRCRv2
43

Knowledge

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

52.1

Qwen2.5-VL-32B

34.7

71
MMLU
43
70
GPQA
42
68
SuperGPQA
40
66
OpenBookQA
38
69
MMLU-Pro
53
7
HLE
2
62
FrontierScience
43

Instruction Following

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

81

Qwen2.5-VL-32B

67

81
IFEval
67

Multilingual

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

77.8

Qwen2.5-VL-32B

60.4

81
MGSM
63
76
MMLU-ProX
59

Mathematics

Ministral 3 14B (Reasoning)

Ministral 3 14B (Reasoning)

75.2

Qwen2.5-VL-32B

49.7

73
AIME 2023
43
75
AIME 2024
45
74
AIME 2025
44
69
HMMT Feb 2023
39
71
HMMT Feb 2024
41
70
HMMT Feb 2025
40
72
BRUMO 2025
42
79
MATH-500
59

Frequently Asked Questions

Which is better, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) is ahead overall, 60 to 38. The biggest single separator in this matchup is MuSR, where the scores are 70 and 39.

Which is better for knowledge tasks, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) has the edge for knowledge tasks in this comparison, averaging 52.1 versus 34.7. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) has the edge for coding in this comparison, averaging 35 versus 14.3. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) has the edge for math in this comparison, averaging 75.2 versus 49.7. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) has the edge for reasoning in this comparison, averaging 69.2 versus 43.2. Inside this category, MuSR is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) has the edge for agentic tasks in this comparison, averaging 58.5 versus 33.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) has the edge for multimodal and grounded tasks in this comparison, averaging 71.5 versus 52.2. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) has the edge for instruction following in this comparison, averaging 81 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Ministral 3 14B (Reasoning) or Qwen2.5-VL-32B?

Ministral 3 14B (Reasoning) has the edge for multilingual tasks in this comparison, averaging 77.8 versus 60.4. Inside this category, MGSM 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.