Qwen3 235B 2507 (Reasoning) vs Ministral 3 3B (Reasoning)

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

Qwen3 235B 2507 (Reasoning) is clearly ahead on the aggregate, 42 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3 235B 2507 (Reasoning)'s sharpest advantage is in coding, where it averages 22.8 against 7.2. The single biggest benchmark swing on the page is SWE-bench Pro, 29 to 6. Ministral 3 3B (Reasoning) does hit back in multilingual, so the answer changes if that is the part of the workload you care about most.

Quick Verdict

Pick Qwen3 235B 2507 (Reasoning) if you want the stronger benchmark profile. Ministral 3 3B (Reasoning) only becomes the better choice if multilingual is the priority.

Agentic

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

45.9

Ministral 3 3B (Reasoning)

34

47
Terminal-Bench 2.0
33
48
BrowseComp
37
43
OSWorld-Verified
33

Coding

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

22.8

Ministral 3 3B (Reasoning)

7.2

32
HumanEval
16
16
SWE-bench Verified
9
18
LiveCodeBench
8
29
SWE-bench Pro
6

Multimodal & Grounded

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

42.1

Ministral 3 3B (Reasoning)

30.4

38
MMMU-Pro
25
47
OfficeQA Pro
37

Reasoning

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

49

Ministral 3 3B (Reasoning)

35.3

38
SimpleQA
26
36
MuSR
26
63
BBH
63
58
LongBench v2
37
58
MRCRv2
40

Knowledge

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

34.1

Ministral 3 3B (Reasoning)

25.2

40
MMLU
25
39
GPQA
24
37
SuperGPQA
22
35
OpenBookQA
20
51
MMLU-Pro
49
6
HLE
1
42
FrontierScience
29

Instruction Following

Tie

Qwen3 235B 2507 (Reasoning)

68

Ministral 3 3B (Reasoning)

68

68
IFEval
68

Multilingual

Ministral 3 3B (Reasoning)

Qwen3 235B 2507 (Reasoning)

58.8

Ministral 3 3B (Reasoning)

59.7

62
MGSM
61
57
MMLU-ProX
59

Mathematics

Qwen3 235B 2507 (Reasoning)

Qwen3 235B 2507 (Reasoning)

48.5

Ministral 3 3B (Reasoning)

40.9

40
AIME 2023
27
42
AIME 2024
29
41
AIME 2025
28
36
HMMT Feb 2023
23
38
HMMT Feb 2024
25
37
HMMT Feb 2025
24
39
BRUMO 2025
26
60
MATH-500
59

Frequently Asked Questions

Which is better, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Qwen3 235B 2507 (Reasoning) is ahead overall, 42 to 31. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 29 and 6.

Which is better for knowledge tasks, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Qwen3 235B 2507 (Reasoning) has the edge for knowledge tasks in this comparison, averaging 34.1 versus 25.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Qwen3 235B 2507 (Reasoning) has the edge for coding in this comparison, averaging 22.8 versus 7.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Qwen3 235B 2507 (Reasoning) has the edge for math in this comparison, averaging 48.5 versus 40.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Qwen3 235B 2507 (Reasoning) has the edge for reasoning in this comparison, averaging 49 versus 35.3. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Qwen3 235B 2507 (Reasoning) has the edge for agentic tasks in this comparison, averaging 45.9 versus 34. 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, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Qwen3 235B 2507 (Reasoning) has the edge for multimodal and grounded tasks in this comparison, averaging 42.1 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Qwen3 235B 2507 (Reasoning) and Ministral 3 3B (Reasoning) are effectively tied for instruction following here, both landing at 68 on average.

Which is better for multilingual tasks, Qwen3 235B 2507 (Reasoning) or Ministral 3 3B (Reasoning)?

Ministral 3 3B (Reasoning) has the edge for multilingual tasks in this comparison, averaging 59.7 versus 58.8. 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.