Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-OSS 20B has the cleaner overall profile here, landing at 35 versus 32. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
GPT-OSS 20B's sharpest advantage is in agentic, where it averages 35.4 against 28.9. The single biggest benchmark swing on the page is LongBench v2, 48 to 38. Ministral 3 8B does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
Pick GPT-OSS 20B if you want the stronger benchmark profile. Ministral 3 8B only becomes the better choice if instruction following is the priority.
GPT-OSS 20B
35.4
Ministral 3 8B
28.9
GPT-OSS 20B
14.5
Ministral 3 8B
14.2
GPT-OSS 20B
36
Ministral 3 8B
32.4
GPT-OSS 20B
40.4
Ministral 3 8B
36.1
GPT-OSS 20B
29
Ministral 3 8B
28
GPT-OSS 20B
67
Ministral 3 8B
69
GPT-OSS 20B
59.7
Ministral 3 8B
61.7
GPT-OSS 20B
43.1
Ministral 3 8B
43.3
GPT-OSS 20B is ahead overall, 35 to 32. The biggest single separator in this matchup is LongBench v2, where the scores are 48 and 38.
GPT-OSS 20B has the edge for knowledge tasks in this comparison, averaging 29 versus 28. 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 14.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Ministral 3 8B has the edge for math in this comparison, averaging 43.3 versus 43.1. 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 36.1. 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 28.9. 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 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Ministral 3 8B has the edge for instruction following in this comparison, averaging 69 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Ministral 3 8B 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.
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.