DeepSeek-R1 vs Granite 4.0 Micro
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
DeepSeek-R1 is the stronger all-rounder.
Scores updated · 21 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-R12 of 3 tests · 1 tie
- CodingWriting and fixing software20DeepSeek-R12 of 2 tests
- FactsGetting facts right instead of making them up20DeepSeek-R12 of 2 tests
- Long documentsFinding answers in very long texts10DeepSeek-R11 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-R11 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-R1 pulls ahead
- Reasons across sets of long documentsAA-LCR+50.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+37.2points ahead
- Code for real scientific research problemsSciCode+26.4points ahead
Where Granite 4.0 Micro pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-R1
- SciCodeDeepSeek-R1 by 26.438.311.9+26.4
- Terminal-Bench HardDeepSeek-R1 by 4.66.11.5+4.6
ReasoningDeepSeek-R1
- GPQA DiamondDeepSeek-R1 by 37.270.833.6+37.2
- Humanity's Last ExamDeepSeek-R1 by 3.58.55+3.5
- CritPttie0.60tie
FactsDeepSeek-R1
- AA-Omniscience · AccuracyDeepSeek-R1 by 21.230.59.3+21.2
- AA-Omniscience · Non-hallucinationDeepSeek-R1 by 5.59.74.2+5.5
Following instructionsDeepSeek-R1
- IFBenchDeepSeek-R1 by 14.23924.8+14.2
Other results11 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.
- AA-OmniscienceDeepSeek-R1 by 45.3-32.2-77.5+45.3
- MMLU-ProDeepSeek-R1 by 39.38444.7+39.3
- HarmBenchGranite 4.0 Micro by 38.447.986.3+38.4
- AIR-Bench 2024Granite 4.0 Micro by 27.552.980.4+27.5
- bbqDeepSeek-R1 by 21.496.675.2+21.4
- Artificial Analysis Coding IndexDeepSeek-R1 by 19.624.65+19.6
- XSTestDeepSeek-R1 by 1994.475.4+19
- AA IntelligenceDeepSeek-R1 by 6.311.45.1+6.3
- anthropic_red_teamGranite 4.0 Micro by 2.497.299.6+2.4
- simple_safety_testsGranite 4.0 Micro by 298100+2
- τ²-Bench Telecom (AA run)Granite 4.0 Micro by 1.211.412.6+1.2
Questions people ask
Which is better, DeepSeek-R1 or Granite 4.0 Micro?
DeepSeek-R1 wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Granite 4.0 Micro wins none. They are level on agents.
Which is better for coding?
DeepSeek-R1. It wins 2 of the 2 coding tests both models report; Granite 4.0 Micro wins none.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.