DeepSeek-V3 vs Gemini 3 Pro
Wins 1 of 6 areas
Facts
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Gemini 3 Pro is the stronger all-rounder.DeepSeek-V3 is cheaper and better at facts.
Scores updated · 38 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 software04Gemini 3 Pro4 of 4 tests
- ReasoningHard problems that need careful thinking04Gemini 3 Pro4 of 4 tests
- Long documentsFinding answers in very long texts02Gemini 3 Pro2 of 2 tests
- Following instructionsDoing exactly what it is asked02Gemini 3 Pro2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Gemini 3 Pro1 of 1 test
- FactsGetting facts right instead of making them up21DeepSeek-V32 of 3 tests
Agents rests on a single test.
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.
DeepSeek-V3 costs 92% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemini 3 Pro pulls ahead
- Common-sense trick questionsSimpleBench+57.5points ahead
- Recent programming contest problemsLiveCodeBench v6+40.5points ahead
- Reasons across sets of long documentsAA-LCR+35.3points ahead
Where DeepSeek-V3 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.6points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3 Pro
- LiveCodeBench v6Gemini 3 Pro by 40.546.987.4+40.5
- SWE-bench VerifiedGemini 3 Pro by 34.24276.2+34.2
- Terminal-Bench HardGemini 3 Pro by 26.515.241.7+26.5
- SciCodeGemini 3 Pro by 17.13956.1+17.1
ReasoningGemini 3 Pro
- SimpleBenchGemini 3 Pro by 57.518.976.4+57.5
- Humanity's Last ExamGemini 3 Pro by 354.739.7+35
- GPQA DiamondGemini 3 Pro by 25.365.590.8+25.3
- CritPtGemini 3 Pro by 9.109.1+9.1
FactsDeepSeek-V3
- AA-Omniscience · AccuracyGemini 3 Pro by 30.325.455.8+30.3
- Vectara HHEM hallucination ratelower is betterDeepSeek-V3 by 7.56.113.6+7.5
- AA-Omniscience · Non-hallucinationDeepSeek-V3 by 5.614.18.5+5.6
Long documentsGemini 3 Pro
- AA-LCRGemini 3 Pro by 35.340.776+35.3
- LongBench v2Gemini 3 Pro by 19.548.768.2+19.5
Following instructionsGemini 3 Pro
- Multi-ChallengeGemini 3 Pro by 34.331.465.7+34.3
- IFBenchGemini 3 Pro by 29.44170.4+29.4
Other results22 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.
- HMMT Feb. 2025Gemini 3 Pro by 68.329.297.5+68.3
- τ²-BenchGemini 3 Pro by 65.532.598+65.5
- AA-OmniscienceGemini 3 Pro by 56-40.715.3+56
- AIME 2025Gemini 3 Pro by 48.751.3100+48.7
- SimpleQAGemini 3 Pro by 47.224.972.1+47.2
- LiveCodeBenchGemini 3 Pro by 42.849.292+42.8
- τ²-Bench Telecom (AA run)Gemini 3 Pro by 4047.187.1+40
- AIR-Bench 2024Gemini 3 Pro by 32.440.873.2+32.4
- Artificial Analysis Coding IndexGemini 3 Pro by 23.52346.5+23.5
- HarmBenchGemini 3 Pro by 22.849.772.5+22.8
- AA IntelligenceGemini 3 Pro by 18.39.728+18.3
- τ²-Bench (Retail)Gemini 3 Pro by 16.269.185.3+16.2
- MMLU-ProGemini 3 Pro by 14.275.990.1+14.2
- MMMLUGemini 3 Pro by 12.479.491.8+12.4
- vectara_factual_consistencyDeepSeek-V3 by 7.593.986.4+7.5
- simple_safety_testsGemini 3 Pro by 2.295.397.5+2.2
- vectara_avg_summary_lengthGemini 3 Pro by 20.2 rating points81.7101.9+20.2 rating
- vectara_answer_rateGemini 3 Pro by 1.997.599.4+1.9
- bbqGemini 3 Pro by 1.796.798.4+1.7
- LiveBenchGemini 3 Pro by 172.473.4+1
- XSTesttie97.197.3tie
- anthropic_red_teamtie97.197tie
Questions people ask
Which is better, DeepSeek-V3 or Gemini 3 Pro?
Gemini 3 Pro wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. DeepSeek-V3 wins facts, and costs 92% less.
Which is better for coding?
Gemini 3 Pro. It wins 4 of the 4 coding tests both models report; DeepSeek-V3 wins none.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Gemini 3 Pro costs $2.00 and $12.00. That makes DeepSeek-V3 about 92% cheaper for the same work.
How do you compare the two?
We use the 38 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 22 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.