Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek-R1 is clearly ahead on the aggregate, 36 to 23. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DeepSeek-R1's sharpest advantage is in mathematics, where it averages 78.3 against 39.7. The single biggest benchmark swing on the page is AIME 2024, 79.8% to 39.7%. Grok 3 Mini does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
DeepSeek-R1 is also the more expensive model on tokens at $0.55 input / $2.19 output per 1M tokens, versus $0.30 input / $0.50 output per 1M tokens for Grok 3 Mini. That is roughly 4.4x on output cost alone. DeepSeek-R1 is the reasoning model in the pair, while Grok 3 Mini is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.
Pick DeepSeek-R1 if you want the stronger benchmark profile. Grok 3 Mini only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Benchmark data for this category is coming soon.
DeepSeek-R1
65.9
Grok 3 Mini
41.5
Benchmark data for this category is coming soon.
DeepSeek-R1
35.6
Grok 3 Mini
21.7
DeepSeek-R1
68.9
Grok 3 Mini
74.1
Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.
Benchmark data for this category is coming soon.
DeepSeek-R1
78.3
Grok 3 Mini
39.7
DeepSeek-R1 is ahead overall, 36 to 23. The biggest single separator in this matchup is AIME 2024, where the scores are 79.8% and 39.7%.
Grok 3 Mini has the edge for knowledge tasks in this comparison, averaging 74.1 versus 68.9. Inside this category, GPQA is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for coding in this comparison, averaging 65.9 versus 41.5. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for math in this comparison, averaging 78.3 versus 39.7. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for reasoning in this comparison, averaging 35.6 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.