DeepSeek-V3 vs Gemma 3 1B Instruct
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Wins 0 of 5 areas
—
DeepSeek-V3 is the stronger all-rounder.
Scores updated · 26 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V31 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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
- Recent programming contest problemsLiveCodeBench v6+42.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+41.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+21.7points ahead
Where Gemma 3 1B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+3.6points ahead
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- LiveCodeBench v6DeepSeek-V3 by 42.646.94.3+42.6
- Terminal-Bench HardDeepSeek-V3 by 15.215.20+15.2
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 41.865.523.7+41.8
- Humanity's Last Examtie4.75.3tie
- CritPttie00tie
FactsEven
- AA-Omniscience · AccuracyDeepSeek-V3 by 21.725.43.8+21.7
- AA-Omniscience · Non-hallucinationGemma 3 1B Instruct by 3.614.117.7+3.6
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 21.14119.9+21.1
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.
- τ²-Bench (Retail)DeepSeek-V3 by 62.769.16.4+62.7
- MMLU-ProDeepSeek-V3 by 61.275.914.7+61.2
- BBHDeepSeek-V3 by 48.487.539.1+48.4
- MMLUDeepSeek-V3 by 48.488.540.1+48.4
- LiveCodeBenchDeepSeek-V3 by 47.349.21.9+47.3
- MATH-500 (EM)DeepSeek-V3 by 4590.245.2+45
- MMMLUDeepSeek-V3 by 4579.434.4+45
- MBPPDeepSeek-V3 by 40.275.435.2+40.2
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 36.647.110.5+36.6
- MGSMDeepSeek-V3 by 36.279.843.6+36.2
- AA-OmniscienceDeepSeek-V3 by 34.7-40.7-75.5+34.7
- GSM8KDeepSeek-V3 by 31.29462.8+31.2
- HumanEvalDeepSeek-V3 by 23.765.241.5+23.7
- τ²-BenchDeepSeek-V3 by 23.132.59.4+23.1
- SimpleQADeepSeek-V3 by 22.724.92.2+22.7
- IFEvalDeepSeek-V3 by 5.986.180.2+5.9
- AA IntelligenceDeepSeek-V3 by 4.99.74.8+4.9
Questions people ask
Which is better, DeepSeek-V3 or Gemma 3 1B Instruct?
DeepSeek-V3 wins four of the five areas where both have results: coding, reasoning, long documents and following instructions. Gemma 3 1B Instruct wins none. They are level on facts.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; Gemma 3 1B Instruct wins none.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 9 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.