DeepSeek-V4-Flash vs Gemini 2.5 Pro
Wins 6 of 7 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
DeepSeek-V4-Flash is the stronger all-rounder.
Scores updated · 31 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-Flash5 of 5 tests
- AgentsCarrying out multi-step tasks on its own40DeepSeek-V4-Flash4 of 4 tests
- ReasoningHard problems that need careful thinking41DeepSeek-V4-Flash4 of 5 tests
- MathCompetition and research-level math20DeepSeek-V4-Flash2 of 2 tests
- Long documentsFinding answers in very long texts10DeepSeek-V4-Flash1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Flash1 of 1 test
- FactsGetting facts right instead of making them up11Even1 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-V4-Flash costs 84% 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-Flash pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+63.3points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+56.5points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+50.2points ahead
Where Gemini 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+21.9points ahead
- Common-sense trick questionsSimpleBench+5.3points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Flash
- Terminal-Bench 2.1DeepSeek-V4-Flash by 50.278.728.5+50.2
- LMArena · WebDevDeepSeek-V4-Flash by 206 rating points14301224+206 rating
- SWE-bench VerifiedDeepSeek-V4-Flash by 15.87963.2+15.8
- Terminal-Bench HardDeepSeek-V4-Flash by 9.135.626.5+9.1
- SciCodeDeepSeek-V4-Flash by 450.346.3+4
AgentsDeepSeek-V4-Flash
- BrowseCompDeepSeek-V4-Flash by 63.373.29.9+63.3
- GDPValDeepSeek-V4-Flash by 46.946.90+46.9
- τ-Bench V3 · BankingDeepSeek-V4-Flash by 29.739.49.7+29.7
- Terminal-Bench 4.0DeepSeek-V4-Flash by 12.112.10+12.1
ReasoningDeepSeek-V4-Flash
- ARC-AGI-2DeepSeek-V4-Flash by 56.561.44.9+56.5
- Humanity's Last ExamDeepSeek-V4-Flash by 20.638.618+20.6
- CritPtDeepSeek-V4-Flash by 1416.62.6+14
- GPQA DiamondDeepSeek-V4-Flash by 7.290.883.6+7.2
- SimpleBenchGemini 2.5 Pro by 5.346.351.6+5.3
FactsEven
- SimpleQA VerifiedGemini 2.5 Pro by 21.934.156+21.9
- AA-Omniscience · AccuracyDeepSeek-V4-Flash by 1.340.439+1.3
- AA-Omniscience · Non-hallucinationtie8.39.1tie
MathDeepSeek-V4-Flash
- FrontierMath Tiers 1-3 (v2)DeepSeek-V4-Flash by 32.957.524.6+32.9
- FrontierMath Tier 4DeepSeek-V4-Flash by 24.424.40+24.4
Long documentsDeepSeek-V4-Flash
- AA-LCRDeepSeek-V4-Flash by 10.779.769+10.7
Following instructionsDeepSeek-V4-Flash
- IFBenchDeepSeek-V4-Flash by 30.579.248.7+30.5
Other results10 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.
- ARC-AGI-1DeepSeek-V4-Flash by 528937+52
- τ²-Bench Telecom (AA run)DeepSeek-V4-Flash by 40.99554.1+40.9
- AA Agentic IndexDeepSeek-V4-Flash by 38.241.73.5+38.2
- Artificial Analysis Coding IndexDeepSeek-V4-Flash by 22.469.146.7+22.4
- OpenAI-MRCR (1M)DeepSeek-V4-Flash by 19.978.758.8+19.9
- AA IntelligenceDeepSeek-V4-Flash by 19.334.315+19.3
- LiveCodeBenchDeepSeek-V4-Flash by 17.491.674.2+17.4
- HLE (with tools)DeepSeek-V4-Flash by 16.745.128.4+16.7
- AA-OmniscienceDeepSeek-V4-Flash by 2-14.3-16.4+2
- MMLU-Protie86.286tie
Questions people ask
Which is better, DeepSeek-V4-Flash or Gemini 2.5 Pro?
DeepSeek-V4-Flash wins six of the seven areas where both have results: coding, agents, reasoning, math, long documents and following instructions. Gemini 2.5 Pro wins none. They are level on facts.
Which is better for coding?
DeepSeek-V4-Flash. It wins 5 of the 5 coding tests both models report; Gemini 2.5 Pro wins none.
Which is cheaper?
DeepSeek-V4-Flash costs $0.44 per million input tokens and $1.32 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. That makes DeepSeek-V4-Flash about 84% cheaper for the same work.
How do you compare the two?
We use the 31 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 10 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.