DeepSeek-V4-Flash-Vision-Exp vs DeepSeek-V4-Pro
Wins 3 of 4 areas
Coding · Reasoning · Following instructions
Wins 1 of 4 areas
Math
DeepSeek-V4-Flash-Vision-Exp is the stronger all-rounder.DeepSeek-V4-Pro is better at math.
Scores updated · 15 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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 software21DeepSeek-V4-Flash-Vision-Exp2 of 3 tests
- ReasoningHard problems that need careful thinking10DeepSeek-V4-Flash-Vision-Exp1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Flash-Vision-Exp1 of 1 test
- MathCompetition and research-level math01DeepSeek-V4-Pro1 of 1 test
Reasoning, math 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-Vision-Exp costs 34% 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-Vision-Exp pulls ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+22.5points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+19.9points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+8.6points ahead
Where DeepSeek-V4-Pro pulls ahead
- Fresh competition math problemsLiveBench · Mathematics+2.9points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+1.8points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Flash-Vision-Exp
- LiveBench · Agentic CodingDeepSeek-V4-Flash-Vision-Exp by 22.565.142.6+22.5
- Terminal-Bench 2.1DeepSeek-V4-Flash-Vision-Exp by 19.983.964+19.9
- LiveBench · CodingDeepSeek-V4-Pro by 1.868.270+1.8
ReasoningDeepSeek-V4-Flash-Vision-Exp
- LiveBench · ReasoningDeepSeek-V4-Flash-Vision-Exp by 2.785.482.7+2.7
Following instructionsDeepSeek-V4-Flash-Vision-Exp
- LiveBench · Instruction FollowingDeepSeek-V4-Flash-Vision-Exp by 8.67162.4+8.6
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.
- DeepSWEDeepSeek-V4-Flash-Vision-Exp by 46.559.312.8+46.5
- DSBench-HardDeepSeek-V4-Flash-Vision-Exp by 32.563.631.1+32.5
- Toolathlon VerifiedDeepSeek-V4-Flash-Vision-Exp by 2075.955.9+20
- NL2RepoDeepSeek-V4-Flash-Vision-Exp by 19.257.738.5+19.2
- AutomationBench PublicDeepSeek-V4-Flash-Vision-Exp by 12.925.712.8+12.9
- CyberGymDeepSeek-V4-Pro by 875.383.3+8
- livebench_data_analysisDeepSeek-V4-Flash-Vision-Exp by 579.574.5+5
- livebench_languageDeepSeek-V4-Flash-Vision-Exp by 2.380.478.1+2.3
- Agents' Last ExamDeepSeek-V4-Flash-Vision-Exp by 1.627.325.7+1.6
Questions people ask
Which is better, DeepSeek-V4-Flash-Vision-Exp or DeepSeek-V4-Pro?
DeepSeek-V4-Flash-Vision-Exp wins three of the four areas where both have results: coding, reasoning and following instructions. DeepSeek-V4-Pro wins math.
Which is better for coding?
DeepSeek-V4-Flash-Vision-Exp. It wins 2 of the 3 coding tests both models report; DeepSeek-V4-Pro wins 1.
Which is cheaper?
DeepSeek-V4-Flash-Vision-Exp costs $0.22 per million input tokens and $0.65 per million output tokens; DeepSeek-V4-Pro costs $0.43 and $0.87. That makes DeepSeek-V4-Flash-Vision-Exp about 34% cheaper for the same work.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 6 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.