GPT-OSS 20B vs Grok 3 Mini

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

Grok 3 Mini is clearly ahead on the aggregate, 23 to 14. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Grok 3 Mini's sharpest advantage is in knowledge, where it averages 74.1 against 29. The single biggest benchmark swing on the page is GPQA, 30% to 66.2%. GPT-OSS 20B does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.

Quick Verdict

Pick Grok 3 Mini if you want the stronger benchmark profile. GPT-OSS 20B only becomes the better choice if reasoning is the priority.

Agentic

Coming soon

Benchmark data for this category is coming soon.

Coding

Grok 3 Mini

GPT-OSS 20B

23

Grok 3 Mini

41.5

23%
HumanEval
Coming soon
Coming soon
LiveCodeBench
41.5%

Multimodal & Grounded

Coming soon

Benchmark data for this category is coming soon.

Reasoning

GPT-OSS 20B

GPT-OSS 20B

27.9

Grok 3 Mini

21.7

29%
SimpleQA
21.7%
27%
MuSR
Coming soon

Knowledge

Grok 3 Mini

GPT-OSS 20B

29

Grok 3 Mini

74.1

31%
MMLU
Coming soon
30%
GPQA
66.2%
28%
SuperGPQA
Coming soon
26%
OpenBookQA
Coming soon
Coming soon
MMLU-Pro
78.9%

Instruction Following

Coming soon

Benchmark data for this category is coming soon.

Multilingual

Coming soon

Benchmark data for this category is coming soon.

Mathematics

Grok 3 Mini

GPT-OSS 20B

30

Grok 3 Mini

39.7

31%
AIME 2023
Coming soon
33%
AIME 2024
39.7%
32%
AIME 2025
Coming soon
27%
HMMT Feb 2023
Coming soon
29%
HMMT Feb 2024
Coming soon
28%
HMMT Feb 2025
Coming soon
30%
BRUMO 2025
Coming soon

Frequently Asked Questions

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

Grok 3 Mini is ahead overall, 23 to 14. The biggest single separator in this matchup is GPQA, where the scores are 30% and 66.2%.

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

Grok 3 Mini has the edge for knowledge tasks in this comparison, averaging 74.1 versus 29. Inside this category, GPQA is the benchmark that creates the most daylight between them.

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

Grok 3 Mini has the edge for coding in this comparison, averaging 41.5 versus 23. GPT-OSS 20B stays close enough that the answer can still flip depending on your workload.

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

Grok 3 Mini has the edge for math in this comparison, averaging 39.7 versus 30. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.

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

GPT-OSS 20B has the edge for reasoning in this comparison, averaging 27.9 versus 21.7. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Last updated: March 17, 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.