DeepSeek-R1 0528 vs Grok 3 Mini Reasoning
Wins 3 of 6 areas
Agents · Reasoning · Facts
Wins 2 of 6 areas
Coding · Following instructions
DeepSeek-R1 0528 wins more areas, narrowly.Grok 3 Mini Reasoning is cheaper and better at coding.
Scores updated · 23 tests both models report · How we compare
Where each one wins
Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking20DeepSeek-R1 05282 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up21DeepSeek-R1 05282 of 3 tests
- AgentsCarrying out multi-step tasks on its own10DeepSeek-R1 05281 of 1 test
- CodingWriting and fixing software01Grok 3 Mini Reasoning1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Grok 3 Mini Reasoning1 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Agents, long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Grok 3 Mini Reasoning costs 82% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where DeepSeek-R1 0528 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+15.4points ahead
- Short factual questions, answered correctlySimpleQA Verified+6.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+4.8points ahead
Where Grok 3 Mini Reasoning pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+57.6points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+6.3points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+1.5points ahead
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGrok 3 Mini Reasoning
- Terminal-Bench HardGrok 3 Mini Reasoning by 1.515.917.4+1.5
- SciCodetie40.340.6tie
ReasoningDeepSeek-R1 0528
- Humanity's Last ExamDeepSeek-R1 0528 by 4.815.811+4.8
- GPQA DiamondDeepSeek-R1 0528 by 2.281.379.1+2.2
- CritPttie1.40.6tie
FactsDeepSeek-R1 0528
- AA-Omniscience · Non-hallucinationGrok 3 Mini Reasoning by 57.616.674.2+57.6
- AA-Omniscience · AccuracyDeepSeek-R1 0528 by 15.430.515.1+15.4
- SimpleQA VerifiedDeepSeek-R1 0528 by 6.327.421.1+6.3
Following instructionsGrok 3 Mini Reasoning
- IFBenchGrok 3 Mini Reasoning by 6.339.645.9+6.3
Other results12 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- τ²-Bench Telecom (AA run)Grok 3 Mini Reasoning by 53.936.590.4+53.9
- AA-OmniscienceGrok 3 Mini Reasoning by 20.6-27.4-6.8+20.6
- livecodebench_hardDeepSeek-R1 0528 by 12.563.651.1+12.5
- AA Agentic IndexGrok 3 Mini Reasoning by 10.420.831.2+10.4
- LiveCodeBenchGrok 3 Mini Reasoning by 7.173.380.4+7.1
- HMMT 2025DeepSeek-R1 0528 by 5.479.474+5.4
- livecodebench_mediumDeepSeek-R1 0528 by 590.985.9+5
- ARC-AGI-1DeepSeek-R1 0528 by 4.721.216.5+4.7
- AIME 2025Grok 3 Mini Reasoning by 3.387.590.8+3.3
- AA IntelligenceGrok 3 Mini Reasoning by 1.513.114.6+1.5
- Artificial Analysis Coding IndexGrok 3 Mini Reasoning by 1.22425.2+1.2
- livecodebench_easyDeepSeek-R1 0528 by 1.199.298.1+1.1
Questions people ask
Which is better, DeepSeek-R1 0528 or Grok 3 Mini Reasoning?
DeepSeek-R1 0528 wins three of the six areas where both have results: agents, reasoning and facts. Grok 3 Mini Reasoning wins coding and following instructions, and costs 82% less. They are level on long documents.
Which is better for coding?
Grok 3 Mini Reasoning. It wins 1 of the 2 coding tests both models report; DeepSeek-R1 0528 wins none, and 1 is a tie.
Which is cheaper?
DeepSeek-R1 0528 costs $1.35 per million input tokens and $3.00 per million output tokens; Grok 3 Mini Reasoning costs $0.30 and $0.50. That makes Grok 3 Mini Reasoning about 82% cheaper for the same work.
How do you compare the two?
We use the 23 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.