GPT-OSS 20B vs Ministral 3 3B

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

GPT-OSS 20B is clearly ahead on the aggregate, 35 to 27. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-OSS 20B's sharpest advantage is in agentic, where it averages 35.4 against 22.9. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 35 to 19.

Quick Verdict

Pick GPT-OSS 20B if you want the stronger benchmark profile. Ministral 3 3B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Agentic

GPT-OSS 20B

GPT-OSS 20B

35.4

Ministral 3 3B

22.9

35
Terminal-Bench 2.0
19
42
BrowseComp
33
31
OSWorld-Verified
20

Coding

GPT-OSS 20B

GPT-OSS 20B

14.5

Ministral 3 3B

6.2

23
HumanEval
15
14
SWE-bench Verified
8
11
LiveCodeBench
7
18
SWE-bench Pro
5

Multimodal & Grounded

GPT-OSS 20B

GPT-OSS 20B

36

Ministral 3 3B

30.4

31
MMMU-Pro
25
42
OfficeQA Pro
37

Reasoning

GPT-OSS 20B

GPT-OSS 20B

40.4

Ministral 3 3B

30.1

29
SimpleQA
22
27
MuSR
20
62
BBH
57
48
LongBench v2
32
48
MRCRv2
35

Knowledge

GPT-OSS 20B

GPT-OSS 20B

29

Ministral 3 3B

24.5

31
MMLU
24
30
GPQA
23
28
SuperGPQA
21
26
OpenBookQA
19
53
MMLU-Pro
48
1
HLE
1
34
FrontierScience
28

Instruction Following

Tie

GPT-OSS 20B

67

Ministral 3 3B

67

67
IFEval
67

Multilingual

Tie

GPT-OSS 20B

59.7

Ministral 3 3B

59.7

61
MGSM
61
59
MMLU-ProX
59

Mathematics

GPT-OSS 20B

GPT-OSS 20B

43.1

Ministral 3 3B

36

31
AIME 2023
23
33
AIME 2024
25
32
AIME 2025
24
27
HMMT Feb 2023
19
29
HMMT Feb 2024
21
28
HMMT Feb 2025
20
30
BRUMO 2025
22
59
MATH-500
53

Frequently Asked Questions

Which is better, GPT-OSS 20B or Ministral 3 3B?

GPT-OSS 20B is ahead overall, 35 to 27. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 35 and 19.

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

GPT-OSS 20B has the edge for knowledge tasks in this comparison, averaging 29 versus 24.5. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-OSS 20B or Ministral 3 3B?

GPT-OSS 20B has the edge for coding in this comparison, averaging 14.5 versus 6.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, GPT-OSS 20B or Ministral 3 3B?

GPT-OSS 20B has the edge for math in this comparison, averaging 43.1 versus 36. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-OSS 20B or Ministral 3 3B?

GPT-OSS 20B has the edge for reasoning in this comparison, averaging 40.4 versus 30.1. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

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

GPT-OSS 20B has the edge for agentic tasks in this comparison, averaging 35.4 versus 22.9. 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-OSS 20B or Ministral 3 3B?

GPT-OSS 20B has the edge for multimodal and grounded tasks in this comparison, averaging 36 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-OSS 20B or Ministral 3 3B?

GPT-OSS 20B and Ministral 3 3B are effectively tied for instruction following here, both landing at 67 on average.

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

GPT-OSS 20B and Ministral 3 3B are effectively tied for multilingual tasks here, both landing at 59.7 on average.

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.