GPT-OSS 120B vs Ministral 3 3B (Reasoning)

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

GPT-OSS 120B is clearly ahead on the aggregate, 48 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-OSS 120B's sharpest advantage is in coding, where it averages 28.1 against 7.2. The single biggest benchmark swing on the page is HumanEval, 43 to 16.

Ministral 3 3B (Reasoning) is the reasoning model in the pair, while GPT-OSS 120B 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.

Quick Verdict

Pick GPT-OSS 120B if you want the stronger benchmark profile. Ministral 3 3B (Reasoning) only becomes the better choice if you want the stronger reasoning-first profile.

Agentic

GPT-OSS 120B

GPT-OSS 120B

44.8

Ministral 3 3B (Reasoning)

34

43
Terminal-Bench 2.0
33
50
BrowseComp
37
43
OSWorld-Verified
33

Coding

GPT-OSS 120B

GPT-OSS 120B

28.1

Ministral 3 3B (Reasoning)

7.2

43
HumanEval
16
29
SWE-bench Verified
9
25
LiveCodeBench
8
31
SWE-bench Pro
6

Multimodal & Grounded

GPT-OSS 120B

GPT-OSS 120B

48.8

Ministral 3 3B (Reasoning)

30.4

42
MMMU-Pro
25
57
OfficeQA Pro
37

Reasoning

GPT-OSS 120B

GPT-OSS 120B

55.2

Ministral 3 3B (Reasoning)

35.3

49
SimpleQA
26
47
MuSR
26
73
BBH
63
58
LongBench v2
37
59
MRCRv2
40

Knowledge

GPT-OSS 120B

GPT-OSS 120B

41.5

Ministral 3 3B (Reasoning)

25.2

51
MMLU
25
50
GPQA
24
48
SuperGPQA
22
46
OpenBookQA
20
63
MMLU-Pro
49
5
HLE
1
49
FrontierScience
29

Instruction Following

GPT-OSS 120B

GPT-OSS 120B

79

Ministral 3 3B (Reasoning)

68

79
IFEval
68

Multilingual

GPT-OSS 120B

GPT-OSS 120B

70.7

Ministral 3 3B (Reasoning)

59.7

72
MGSM
61
70
MMLU-ProX
59

Mathematics

GPT-OSS 120B

GPT-OSS 120B

59.5

Ministral 3 3B (Reasoning)

40.9

51
AIME 2023
27
53
AIME 2024
29
52
AIME 2025
28
47
HMMT Feb 2023
23
49
HMMT Feb 2024
25
48
HMMT Feb 2025
24
50
BRUMO 2025
26
71
MATH-500
59

Frequently Asked Questions

Which is better, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B is ahead overall, 48 to 31. The biggest single separator in this matchup is HumanEval, where the scores are 43 and 16.

Which is better for knowledge tasks, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B has the edge for knowledge tasks in this comparison, averaging 41.5 versus 25.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B has the edge for coding in this comparison, averaging 28.1 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B has the edge for math in this comparison, averaging 59.5 versus 40.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B has the edge for reasoning in this comparison, averaging 55.2 versus 35.3. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B has the edge for agentic tasks in this comparison, averaging 44.8 versus 34. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B has the edge for multimodal and grounded tasks in this comparison, averaging 48.8 versus 30.4. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B has the edge for instruction following in this comparison, averaging 79 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-OSS 120B or Ministral 3 3B (Reasoning)?

GPT-OSS 120B has the edge for multilingual tasks in this comparison, averaging 70.7 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.