DeepSeek-V3 vs Phi 3 Mini 4K Instruct
Wins 4 of 4 areas
Coding · Reasoning · Long documents · Following instructions
Wins 0 of 4 areas
—
DeepSeek-V3 is the stronger all-rounder.
Scores updated · 18 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
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
- Reasons across sets of long documentsAA-LCR+37.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+33.6points ahead
- Code for real scientific research problemsSciCode+30points ahead
Where Phi 3 Mini 4K Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- SciCodeDeepSeek-V3 by 30399+30
- Terminal-Bench HardDeepSeek-V3 by 15.215.20+15.2
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 33.665.531.9+33.6
- Humanity's Last Examtie4.75tie
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 17.14123.9+17.1
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)DeepSeek-V3 by 47.147.10+47.1
- MATHDeepSeek-V3 by 39.690.250.6+39.6
- Artificial Analysis Coding IndexDeepSeek-V3 by 20233+20
- MMLUDeepSeek-V3 by 17.688.570.9+17.6
- HellaSwagDeepSeek-V3 by 13.688.975.3+13.6
- WinoGrandeDeepSeek-V3 by 13.384.971.6+13.3
- OpenBookQADeepSeek-V3 by 13.295.482.2+13.2
- ARC-ChallengeDeepSeek-V3 by 995.386.3+9
- HumanEvalDeepSeek-V3 by 7.965.257.3+7.9
- MBPPDeepSeek-V3 by 5.675.469.8+5.6
- AA IntelligenceDeepSeek-V3 by 3.99.75.8+3.9
- PIQADeepSeek-V3 by 1.284.783.5+1.2
Questions people ask
Which is better, DeepSeek-V3 or Phi 3 Mini 4K Instruct?
DeepSeek-V3 wins all four areas where both have results: coding, reasoning, long documents and following instructions. Phi 3 Mini 4K Instruct wins none.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; Phi 3 Mini 4K Instruct wins none.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 6 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.