DeepSeek-V3.2-Exp vs Gemini 2.5 Pro
Wins 5 of 6 areas
Coding · Agents · Facts · Long documents · Following instructions
Wins 1 of 6 areas
Reasoning
DeepSeek-V3.2-Exp is the stronger all-rounder.Gemini 2.5 Pro is better at reasoning.
Scores updated · 32 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 software31DeepSeek-V3.2-Exp3 of 4 tests
- AgentsCarrying out multi-step tasks on its own20DeepSeek-V3.2-Exp2 of 2 tests
- FactsGetting facts right instead of making them up21DeepSeek-V3.2-Exp2 of 3 tests
- Long documentsFinding answers in very long texts10DeepSeek-V3.2-Exp1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V3.2-Exp1 of 1 test
- ReasoningHard problems that need careful thinking03Gemini 2.5 Pro3 of 3 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-V3.2-Exp costs 94% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where DeepSeek-V3.2-Exp pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+30.2points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5.4points ahead
Where Gemini 2.5 Pro pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.5points ahead
- Code for real scientific research problemsSciCode+8.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.9points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3.2-Exp
- SciCodeGemini 2.5 Pro by 8.637.746.3+8.6
- LMArena · WebDevDeepSeek-V3.2-Exp by 48 rating points12721224+48 rating
- SWE-bench VerifiedDeepSeek-V3.2-Exp by 4.667.863.2+4.6
- Terminal-Bench HardDeepSeek-V3.2-Exp by 4.631.126.5+4.6
AgentsDeepSeek-V3.2-Exp
- BrowseCompDeepSeek-V3.2-Exp by 30.240.19.9+30.2
- GDPValDeepSeek-V3.2-Exp by 25250+25
ReasoningGemini 2.5 Pro
- GPQA DiamondGemini 2.5 Pro by 3.979.783.6+3.9
- Humanity's Last ExamGemini 2.5 Pro by 3.114.918+3.1
- CritPtGemini 2.5 Pro by 1.21.42.6+1.2
FactsDeepSeek-V3.2-Exp
- AA-Omniscience · AccuracyGemini 2.5 Pro by 11.527.639+11.5
- AA-Omniscience · Non-hallucinationDeepSeek-V3.2-Exp by 10.119.29.1+10.1
- Vectara HHEM hallucination ratelower is betterDeepSeek-V3.2-Exp by 1.75.37+1.7
Following instructionsDeepSeek-V3.2-Exp
- IFBenchDeepSeek-V3.2-Exp by 5.454.148.7+5.4
Other results18 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.
- SimpleQADeepSeek-V3.2-Exp by 46.397.150.8+46.3
- AA Agentic IndexDeepSeek-V3.2-Exp by 25.228.73.5+25.2
- τ²-Bench Telecom (AA run)Gemini 2.5 Pro by 20.233.954.1+20.2
- HMMT 2025DeepSeek-V3.2-Exp by 17.983.665.7+17.9
- BrowseComp-ZHDeepSeek-V3.2-Exp by 15.747.932.2+15.7
- AA-OmniscienceGemini 2.5 Pro by 14.7-31-16.4+14.7
- Artificial Analysis Coding IndexGemini 2.5 Pro by 13.433.346.7+13.4
- Terminal-BenchDeepSeek-V3.2-Exp by 12.437.725.3+12.4
- HMMT Feb. 2025DeepSeek-V3.2-Exp by 9.29080.8+9.2
- AIME 2025DeepSeek-V3.2-Exp by 6.389.383+6.3
- HMMT Nov. 2025DeepSeek-V3.2-Exp by 4.284.280+4.2
- vectara_avg_summary_lengthGemini 2.5 Pro by 41.8 rating points64.6106.4+41.8 rating
- vectara_answer_rateGemini 2.5 Pro by 2.596.699.1+2.5
- Aider-PolyglotGemini 2.5 Pro by 274.576.5+2
- vectara_factual_consistencyDeepSeek-V3.2-Exp by 1.794.793+1.7
- AA IntelligenceDeepSeek-V3.2-Exp by 1.616.615+1.6
- MMLU-ProGemini 2.5 Pro by 18586+1
- LiveCodeBenchtie74.174.2tie
Questions people ask
Which is better, DeepSeek-V3.2-Exp or Gemini 2.5 Pro?
DeepSeek-V3.2-Exp wins five of the six areas where both have results: coding, agents, facts, long documents and following instructions. Gemini 2.5 Pro wins reasoning.
Which is better for coding?
DeepSeek-V3.2-Exp. It wins 3 of the 4 coding tests both models report; Gemini 2.5 Pro wins 1.
Which is cheaper?
DeepSeek-V3.2-Exp costs $0.28 per million input tokens and $0.42 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. That makes DeepSeek-V3.2-Exp about 94% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.