DeepSeek-V4-Pro vs Gemini 2.5 Pro
Wins 6 of 7 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Wins 1 of 7 areas
Facts
DeepSeek-V4-Pro is the stronger all-rounder.Gemini 2.5 Pro is better at facts.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software50DeepSeek-V4-Pro5 of 5 tests
- AgentsCarrying out multi-step tasks on its own40DeepSeek-V4-Pro4 of 4 tests
- ReasoningHard problems that need careful thinking30DeepSeek-V4-Pro3 of 4 tests · 1 tie
- MathCompetition and research-level math20DeepSeek-V4-Pro2 of 2 tests
- Long documentsFinding answers in very long texts10DeepSeek-V4-Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Pro1 of 1 test
- FactsGetting facts right instead of making them up13Gemini 2.5 Pro3 of 4 tests
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.
DeepSeek-V4-Pro costs 88% 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 DeepSeek-V4-Pro pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+73.5points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+35.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+27.8points ahead
Where Gemini 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+9.8points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+3.2points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Pro
- Terminal-Bench 2.1DeepSeek-V4-Pro by 35.56428.5+35.5
- LMArena · WebDevDeepSeek-V4-Pro by 240 rating points14641224+240 rating
- Terminal-Bench HardDeepSeek-V4-Pro by 19.746.226.5+19.7
- SWE-bench VerifiedDeepSeek-V4-Pro by 17.480.663.2+17.4
- SciCodeDeepSeek-V4-Pro by 4.550.846.3+4.5
AgentsDeepSeek-V4-Pro
- BrowseCompDeepSeek-V4-Pro by 73.583.49.9+73.5
- GDPValDeepSeek-V4-Pro by 32.932.90+32.9
- τ-Bench V3 · BankingDeepSeek-V4-Pro by 20.430.19.7+20.4
- Terminal-Bench 4.0DeepSeek-V4-Pro by 14.614.60+14.6
ReasoningDeepSeek-V4-Pro
- Humanity's Last ExamDeepSeek-V4-Pro by 19.537.518+19.5
- CritPtDeepSeek-V4-Pro by 10.312.92.6+10.3
- GPQA DiamondDeepSeek-V4-Pro by 5.288.883.6+5.2
- SimpleBenchtie50.951.6tie
FactsGemini 2.5 Pro
- SimpleQA VerifiedGemini 2.5 Pro by 9.846.256+9.8
- AA-Omniscience · AccuracyDeepSeek-V4-Pro by 3.94339+3.9
- AA-Omniscience · Non-hallucinationGemini 2.5 Pro by 3.25.99.1+3.2
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 1.68.67+1.6
MathDeepSeek-V4-Pro
- FrontierMath Tiers 1-3 (v2)DeepSeek-V4-Pro by 20.745.324.6+20.7
- FrontierMath Tier 4DeepSeek-V4-Pro by 2.42.40+2.4
Following instructionsDeepSeek-V4-Pro
- IFBenchDeepSeek-V4-Pro by 27.876.548.7+27.8
Other results15 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-V4-Pro by 42.196.254.1+42.1
- HLE (with tools)DeepSeek-V4-Pro by 31.66028.4+31.6
- OpenAI-MRCR (1M)DeepSeek-V4-Pro by 24.583.358.8+24.5
- AA Agentic IndexDeepSeek-V4-Pro by 24.227.73.5+24.2
- LiveCodeBenchDeepSeek-V4-Pro by 19.393.574.2+19.3
- AA IntelligenceDeepSeek-V4-Pro by 15.430.415+15.4
- HMMT Nov. 2025DeepSeek-V4-Pro by 14.494.480+14.4
- Artificial Analysis Coding IndexDeepSeek-V4-Pro by 12.759.446.7+12.7
- SimpleQADeepSeek-V4-Pro by 7.157.950.8+7.1
- AA-OmniscienceDeepSeek-V4-Pro by 5.6-10.7-16.4+5.6
- vectara_avg_summary_lengthDeepSeek-V4-Pro by 47.4 rating points153.8106.4+47.4 rating
- vectara_answer_rateGemini 2.5 Pro by 1.997.299.1+1.9
- vectara_factual_consistencyGemini 2.5 Pro by 1.691.493+1.6
- MMLU-ProDeepSeek-V4-Pro by 1.587.586+1.5
- Global-MMLU-Litetie89.388.6tie
Questions people ask
Which is better, DeepSeek-V4-Pro or Gemini 2.5 Pro?
DeepSeek-V4-Pro wins six of the seven areas where both have results: coding, agents, reasoning, math, long documents and following instructions. Gemini 2.5 Pro wins facts.
Which is better for coding?
DeepSeek-V4-Pro. It wins 5 of the 5 coding tests both models report; Gemini 2.5 Pro wins none.
Which is cheaper?
DeepSeek-V4-Pro costs $0.43 per million input tokens and $0.87 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. That makes DeepSeek-V4-Pro about 88% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.