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.
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.
GPT-OSS 20B
35.4
Ministral 3 3B
22.9
GPT-OSS 20B
14.5
Ministral 3 3B
6.2
GPT-OSS 20B
36
Ministral 3 3B
30.4
GPT-OSS 20B
40.4
Ministral 3 3B
30.1
GPT-OSS 20B
29
Ministral 3 3B
24.5
GPT-OSS 20B
67
Ministral 3 3B
67
GPT-OSS 20B
59.7
Ministral 3 3B
59.7
GPT-OSS 20B
43.1
Ministral 3 3B
36
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.
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.
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.
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.
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.
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.
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.
GPT-OSS 20B and Ministral 3 3B are effectively tied for instruction following here, both landing at 67 on average.
GPT-OSS 20B and Ministral 3 3B are effectively tied for multilingual tasks here, both landing at 59.7 on average.
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.