GPT-5 (medium) vs Ministral 3 3B (Reasoning)

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

GPT-5 (medium) is clearly ahead on the aggregate, 78 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5 (medium)'s sharpest advantage is in coding, where it averages 66.1 against 7.2. The single biggest benchmark swing on the page is HumanEval, 83 to 16.

Quick Verdict

Pick GPT-5 (medium) if you want the stronger benchmark profile. Ministral 3 3B (Reasoning) only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Agentic

GPT-5 (medium)

GPT-5 (medium)

75.5

Ministral 3 3B (Reasoning)

34

77
Terminal-Bench 2.0
33
78
BrowseComp
37
72
OSWorld-Verified
33

Coding

GPT-5 (medium)

GPT-5 (medium)

66.1

Ministral 3 3B (Reasoning)

7.2

83
HumanEval
16
67
SWE-bench Verified
9
60
LiveCodeBench
8
72
SWE-bench Pro
6

Multimodal & Grounded

GPT-5 (medium)

GPT-5 (medium)

88.1

Ministral 3 3B (Reasoning)

30.4

89
MMMU-Pro
25
87
OfficeQA Pro
37

Reasoning

GPT-5 (medium)

GPT-5 (medium)

84.3

Ministral 3 3B (Reasoning)

35.3

87
SimpleQA
26
85
MuSR
26
92
BBH
63
81
LongBench v2
37
81
MRCRv2
40

Knowledge

GPT-5 (medium)

GPT-5 (medium)

69.8

Ministral 3 3B (Reasoning)

25.2

91
MMLU
25
89
GPQA
24
87
SuperGPQA
22
85
OpenBookQA
20
81
MMLU-Pro
49
27
HLE
1
82
FrontierScience
29

Instruction Following

GPT-5 (medium)

GPT-5 (medium)

88

Ministral 3 3B (Reasoning)

68

88
IFEval
68

Multilingual

GPT-5 (medium)

GPT-5 (medium)

88.1

Ministral 3 3B (Reasoning)

59.7

90
MGSM
61
87
MMLU-ProX
59

Mathematics

GPT-5 (medium)

GPT-5 (medium)

92

Ministral 3 3B (Reasoning)

40.9

93
AIME 2023
27
95
AIME 2024
29
94
AIME 2025
28
89
HMMT Feb 2023
23
91
HMMT Feb 2024
25
90
HMMT Feb 2025
24
92
BRUMO 2025
26
92
MATH-500
59

Frequently Asked Questions

Which is better, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) is ahead overall, 78 to 31. The biggest single separator in this matchup is HumanEval, where the scores are 83 and 16.

Which is better for knowledge tasks, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) has the edge for knowledge tasks in this comparison, averaging 69.8 versus 25.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) has the edge for coding in this comparison, averaging 66.1 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) has the edge for math in this comparison, averaging 92 versus 40.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) has the edge for reasoning in this comparison, averaging 84.3 versus 35.3. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) has the edge for agentic tasks in this comparison, averaging 75.5 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, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) has the edge for multimodal and grounded tasks in this comparison, averaging 88.1 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) has the edge for instruction following in this comparison, averaging 88 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5 (medium) or Ministral 3 3B (Reasoning)?

GPT-5 (medium) has the edge for multilingual tasks in this comparison, averaging 88.1 versus 59.7. 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.