Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Grok 3 Mini has the cleaner overall profile here, landing at 23 versus 20. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Grok 3 Mini's sharpest advantage is in coding, where it averages 41.5 against 25. The single biggest benchmark swing on the page is AIME 2024, 66.3% to 39.7%. DeepSeek V3.1 does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.
Pick Grok 3 Mini if you want the stronger benchmark profile. DeepSeek V3.1 only becomes the better choice if reasoning is the priority.
Benchmark data for this category is coming soon.
DeepSeek V3.1
25
Grok 3 Mini
41.5
Benchmark data for this category is coming soon.
DeepSeek V3.1
29.9
Grok 3 Mini
21.7
DeepSeek V3.1
66.7
Grok 3 Mini
74.1
Benchmark data for this category is coming soon.
Benchmark data for this category is coming soon.
DeepSeek V3.1
32
Grok 3 Mini
39.7
Grok 3 Mini is ahead overall, 23 to 20. The biggest single separator in this matchup is AIME 2024, where the scores are 66.3% and 39.7%.
Grok 3 Mini has the edge for knowledge tasks in this comparison, averaging 74.1 versus 66.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Grok 3 Mini has the edge for coding in this comparison, averaging 41.5 versus 25. DeepSeek V3.1 stays close enough that the answer can still flip depending on your workload.
Grok 3 Mini has the edge for math in this comparison, averaging 39.7 versus 32. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
DeepSeek V3.1 has the edge for reasoning in this comparison, averaging 29.9 versus 21.7. Inside this category, SimpleQA 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.