Ministral 3 8B (Reasoning) vs GPT-OSS 20B

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

Ministral 3 8B (Reasoning) finishes one point ahead overall, 36 to 35. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.

Ministral 3 8B (Reasoning)'s sharpest advantage is in mathematics, where it averages 47.8 against 43.1. The single biggest benchmark swing on the page is BBH, 70 to 62. GPT-OSS 20B does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.

Ministral 3 8B (Reasoning) is the reasoning model in the pair, while GPT-OSS 20B 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 Ministral 3 8B (Reasoning) if you want the stronger benchmark profile. GPT-OSS 20B only becomes the better choice if multimodal & grounded is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

Ministral 3 8B (Reasoning)

Ministral 3 8B (Reasoning)

38.5

GPT-OSS 20B

35.4

39
Terminal-Bench 2.0
35
41
BrowseComp
42
36
OSWorld-Verified
31

Coding

Ministral 3 8B (Reasoning)

Ministral 3 8B (Reasoning)

15.2

GPT-OSS 20B

14.5

24
HumanEval
23
17
SWE-bench Verified
14
16
LiveCodeBench
11
14
SWE-bench Pro
18

Multimodal & Grounded

GPT-OSS 20B

Ministral 3 8B (Reasoning)

33.4

GPT-OSS 20B

36

28
MMMU-Pro
31
40
OfficeQA Pro
42

Reasoning

Ministral 3 8B (Reasoning)

Ministral 3 8B (Reasoning)

42.1

GPT-OSS 20B

40.4

32
SimpleQA
29
33
MuSR
27
70
BBH
62
44
LongBench v2
48
47
MRCRv2
48

Knowledge

Ministral 3 8B (Reasoning)

Ministral 3 8B (Reasoning)

30

GPT-OSS 20B

29

30
MMLU
31
29
GPQA
30
27
SuperGPQA
28
25
OpenBookQA
26
54
MMLU-Pro
53
5
HLE
1
34
FrontierScience
34

Instruction Following

Ministral 3 8B (Reasoning)

Ministral 3 8B (Reasoning)

70

GPT-OSS 20B

67

70
IFEval
67

Multilingual

Ministral 3 8B (Reasoning)

Ministral 3 8B (Reasoning)

61.7

GPT-OSS 20B

59.7

63
MGSM
61
61
MMLU-ProX
59

Mathematics

Ministral 3 8B (Reasoning)

Ministral 3 8B (Reasoning)

47.8

GPT-OSS 20B

43.1

33
AIME 2023
31
35
AIME 2024
33
34
AIME 2025
32
29
HMMT Feb 2023
27
31
HMMT Feb 2024
29
30
HMMT Feb 2025
28
32
BRUMO 2025
30
67
MATH-500
59

Frequently Asked Questions

Which is better, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

Ministral 3 8B (Reasoning) is ahead overall, 36 to 35. The biggest single separator in this matchup is BBH, where the scores are 70 and 62.

Which is better for knowledge tasks, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

Ministral 3 8B (Reasoning) has the edge for knowledge tasks in this comparison, averaging 30 versus 29. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

Ministral 3 8B (Reasoning) has the edge for coding in this comparison, averaging 15.2 versus 14.5. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.

Which is better for math, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

Ministral 3 8B (Reasoning) has the edge for math in this comparison, averaging 47.8 versus 43.1. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

Ministral 3 8B (Reasoning) has the edge for reasoning in this comparison, averaging 42.1 versus 40.4. Inside this category, BBH is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

Ministral 3 8B (Reasoning) has the edge for agentic tasks in this comparison, averaging 38.5 versus 35.4. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

GPT-OSS 20B has the edge for multimodal and grounded tasks in this comparison, averaging 36 versus 33.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

Ministral 3 8B (Reasoning) has the edge for instruction following in this comparison, averaging 70 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Ministral 3 8B (Reasoning) or GPT-OSS 20B?

Ministral 3 8B (Reasoning) has the edge for multilingual tasks in this comparison, averaging 61.7 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.