GPT-OSS 120B vs Ministral 3 8B (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 36. 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 multimodal & grounded, where it averages 48.8 against 33.4. The single biggest benchmark swing on the page is MMLU, 51 to 30.

Ministral 3 8B (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 8B (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 8B (Reasoning)

38.5

43
Terminal-Bench 2.0
39
50
BrowseComp
41
43
OSWorld-Verified
36

Coding

GPT-OSS 120B

GPT-OSS 120B

28.1

Ministral 3 8B (Reasoning)

15.2

43
HumanEval
24
29
SWE-bench Verified
17
25
LiveCodeBench
16
31
SWE-bench Pro
14

Multimodal & Grounded

GPT-OSS 120B

GPT-OSS 120B

48.8

Ministral 3 8B (Reasoning)

33.4

42
MMMU-Pro
28
57
OfficeQA Pro
40

Reasoning

GPT-OSS 120B

GPT-OSS 120B

55.2

Ministral 3 8B (Reasoning)

42.1

49
SimpleQA
32
47
MuSR
33
73
BBH
70
58
LongBench v2
44
59
MRCRv2
47

Knowledge

GPT-OSS 120B

GPT-OSS 120B

41.5

Ministral 3 8B (Reasoning)

30

51
MMLU
30
50
GPQA
29
48
SuperGPQA
27
46
OpenBookQA
25
63
MMLU-Pro
54
5
HLE
5
49
FrontierScience
34

Instruction Following

GPT-OSS 120B

GPT-OSS 120B

79

Ministral 3 8B (Reasoning)

70

79
IFEval
70

Multilingual

GPT-OSS 120B

GPT-OSS 120B

70.7

Ministral 3 8B (Reasoning)

61.7

72
MGSM
63
70
MMLU-ProX
61

Mathematics

GPT-OSS 120B

GPT-OSS 120B

59.5

Ministral 3 8B (Reasoning)

47.8

51
AIME 2023
33
53
AIME 2024
35
52
AIME 2025
34
47
HMMT Feb 2023
29
49
HMMT Feb 2024
31
48
HMMT Feb 2025
30
50
BRUMO 2025
32
71
MATH-500
67

Frequently Asked Questions

Which is better, GPT-OSS 120B or Ministral 3 8B (Reasoning)?

GPT-OSS 120B is ahead overall, 48 to 36. The biggest single separator in this matchup is MMLU, where the scores are 51 and 30.

Which is better for knowledge tasks, GPT-OSS 120B or Ministral 3 8B (Reasoning)?

GPT-OSS 120B has the edge for knowledge tasks in this comparison, averaging 41.5 versus 30. 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 8B (Reasoning)?

GPT-OSS 120B has the edge for coding in this comparison, averaging 28.1 versus 15.2. 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 8B (Reasoning)?

GPT-OSS 120B has the edge for math in this comparison, averaging 59.5 versus 47.8. 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 8B (Reasoning)?

GPT-OSS 120B has the edge for reasoning in this comparison, averaging 55.2 versus 42.1. 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 8B (Reasoning)?

GPT-OSS 120B has the edge for agentic tasks in this comparison, averaging 44.8 versus 38.5. 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 8B (Reasoning)?

GPT-OSS 120B has the edge for multimodal and grounded tasks in this comparison, averaging 48.8 versus 33.4. 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 8B (Reasoning)?

GPT-OSS 120B has the edge for instruction following in this comparison, averaging 79 versus 70. 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 8B (Reasoning)?

GPT-OSS 120B has the edge for multilingual tasks in this comparison, averaging 70.7 versus 61.7. 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.