DeepSeek-V3 vs Phi 4 Mini Instruct
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
DeepSeek-V3 is the stronger all-rounder.
Scores updated · 29 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.
- CodingWriting and fixing software20DeepSeek-V32 of 2 tests
- ReasoningHard problems that need careful thinking10DeepSeek-V31 of 3 tests · 2 ties
- FactsGetting facts right instead of making them up21DeepSeek-V32 of 3 tests
- AgentsCarrying out multi-step tasks on its own10DeepSeek-V31 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V31 of 1 test
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-V3 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+32.4points ahead
- Code for real scientific research problemsSciCode+28.2points ahead
- Reasons across sets of long documentsAA-LCR+25.4points ahead
Where Phi 4 Mini Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+7.9points ahead
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- SciCodeDeepSeek-V3 by 28.23910.8+28.2
- Terminal-Bench HardDeepSeek-V3 by 15.215.20+15.2
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 32.465.533.1+32.4
- Humanity's Last Examtie4.74.5tie
- CritPttie00tie
FactsDeepSeek-V3
- Vectara HHEM hallucination ratelower is betterDeepSeek-V3 by 17.46.123.5+17.4
- AA-Omniscience · AccuracyDeepSeek-V3 by 1625.49.5+16
- AA-Omniscience · Non-hallucinationPhi 4 Mini Instruct by 7.914.122+7.9
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 19.94121.1+19.9
Other results17 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.
- Arena HardDeepSeek-V3 by 58.691.432.8+58.6
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 38.947.18.2+38.9
- vectara_avg_summary_lengthPhi 4 Mini Instruct by 338.5 rating points81.7420.2+338.5 rating
- MMLU-ProDeepSeek-V3 by 23.175.952.8+23.1
- AA-OmniscienceDeepSeek-V3 by 20.4-40.7-61.1+20.4
- HellaSwagDeepSeek-V3 by 19.888.969.1+19.8
- Artificial Analysis Coding IndexDeepSeek-V3 by 19.2233.8+19.2
- WinoGrandeDeepSeek-V3 by 17.984.967+17.9
- vectara_factual_consistencyDeepSeek-V3 by 17.493.976.5+17.4
- BBHDeepSeek-V3 by 17.187.570.4+17.1
- OpenBookQADeepSeek-V3 by 16.295.479.2+16.2
- MGSMDeepSeek-V3 by 15.979.863.9+15.9
- ARC-ChallengeDeepSeek-V3 by 11.695.383.7+11.6
- PIQADeepSeek-V3 by 7.184.777.6+7.1
- GSM8KDeepSeek-V3 by 5.49488.6+5.4
- vectara_answer_rateDeepSeek-V3 by 597.592.5+5
- AA IntelligenceDeepSeek-V3 by 3.49.76.3+3.4
Questions people ask
Which is better, DeepSeek-V3 or Phi 4 Mini Instruct?
DeepSeek-V3 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Phi 4 Mini Instruct wins none.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; Phi 4 Mini Instruct wins none.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.