DeepSeek-V3.2 vs Gemini 3.5 Flash
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Following instructions
Gemini 3.5 Flash is the stronger all-rounder.DeepSeek-V3.2 is cheaper.
Scores updated · 29 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 software05Gemini 3.5 Flash5 of 5 tests
- AgentsCarrying out multi-step tasks on its own04Gemini 3.5 Flash4 of 4 tests
- ReasoningHard problems that need careful thinking04Gemini 3.5 Flash4 of 4 tests
- FactsGetting facts right instead of making them up03Gemini 3.5 Flash3 of 3 tests
- MathCompetition and research-level math01Gemini 3.5 Flash1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Gemini 3.5 Flash1 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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 costs 93% 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 3.5 Flash pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+68.1points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+39.5points ahead
- Short factual questions, answered correctlySimpleQA Verified+38.7points ahead
Where DeepSeek-V3.2 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.5 Flash
- SWE-bench ProGemini 3.5 Flash by 39.515.655.1+39.5
- Terminal-Bench 2.1Gemini 3.5 Flash by 31.946.878.7+31.9
- SciCodeGemini 3.5 Flash by 1538.953.9+15
- LMArena · WebDevGemini 3.5 Flash by 137 rating points13621499+137 rating
- Terminal-Bench HardGemini 3.5 Flash by 5.335.640.9+5.3
AgentsGemini 3.5 Flash
- AA ApexAgentsGemini 3.5 Flash by 32.614.547.1+32.6
- GDPValGemini 3.5 Flash by 25.49.835.2+25.4
- MCP AtlasGemini 3.5 Flash by 21.462.283.6+21.4
- τ-Bench V3 · BankingGemini 3.5 Flash by 13.418.832.2+13.4
ReasoningGemini 3.5 Flash
- ARC-AGI-2Gemini 3.5 Flash by 68.1472.1+68.1
- Humanity's Last ExamGemini 3.5 Flash by 18.124.642.7+18.1
- CritPtGemini 3.5 Flash by 10.22.913.1+10.2
- GPQA DiamondGemini 3.5 Flash by 8.28492.2+8.2
FactsGemini 3.5 Flash
- SimpleQA VerifiedGemini 3.5 Flash by 38.727.566.2+38.7
- AA-Omniscience · Non-hallucinationGemini 3.5 Flash by 20.517.337.8+20.5
- AA-Omniscience · AccuracyGemini 3.5 Flash by 18.43351.4+18.4
MathGemini 3.5 Flash
- HMMT Feb. 2026Gemini 3.5 Flash by 11.484.195.5+11.4
- AIME 2026tie94.295tie
Following instructionsGemini 3.5 Flash
- IFBenchGemini 3.5 Flash by 15.660.776.3+15.6
Other results9 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.
- AA-OmniscienceGemini 3.5 Flash by 43.7-22.521.2+43.7
- ARC-AGI-1Gemini 3.5 Flash by 35.55792.5+35.5
- Terminal-Bench 2.0Gemini 3.5 Flash by 29.846.476.2+29.8
- Artificial Analysis Coding IndexGemini 3.5 Flash by 25.944.270.1+25.9
- ToolathlonGemini 3.5 Flash by 21.335.256.5+21.3
- frontiermath_tier_4_v1Gemini 3.5 Flash by 12.52.114.6+12.5
- AA IntelligenceGemini 3.5 Flash by 11.121.532.6+11.1
- AA Agentic IndexGemini 3.5 Flash by 918.327.3+9
- τ²-Bench Telecom (AA run)Gemini 3.5 Flash by 4.790.695.3+4.7
Questions people ask
Which is better, DeepSeek-V3.2 or Gemini 3.5 Flash?
Gemini 3.5 Flash wins six of the seven areas where both have results: coding, agents, reasoning, facts, math and following instructions. DeepSeek-V3.2 wins none, but costs 93% less. They are level on long documents.
Which is better for coding?
Gemini 3.5 Flash. It wins 5 of the 5 coding tests both models report; DeepSeek-V3.2 wins none.
Which is cheaper?
DeepSeek-V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens; Gemini 3.5 Flash costs $1.50 and $9.00. That makes DeepSeek-V3.2 about 93% cheaper for the same work.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 20 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.