Claude Sonnet 4 vs DeepSeek-V4-Flash
Wins 0 of 6 areas
—
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
DeepSeek-V4-Flash is the stronger all-rounder.
Scores updated · 28 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 software07DeepSeek-V4-Flash7 of 7 tests
- ReasoningHard problems that need careful thinking04DeepSeek-V4-Flash4 of 5 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own03DeepSeek-V4-Flash3 of 3 tests
- Long documentsFinding answers in very long texts01DeepSeek-V4-Flash1 of 1 test
- Following instructionsDoing exactly what it is asked01DeepSeek-V4-Flash1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 90% 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+61points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+55.5points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+42.4points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+62.6points ahead
Every test, side by side
All 28 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 42.436.378.7+42.4
- LiveCodeBench v6DeepSeek-V4-Flash by 42.148.590.6+42.1
- SWE-bench MultilingualDeepSeek-V4-Flash by 16.456.973.3+16.4
- SciCodeDeepSeek-V4-Flash by 10.34050.3+10.3
- SWE-bench ProDeepSeek-V4-Flash by 9.942.752.6+9.9
- SWE-bench VerifiedDeepSeek-V4-Flash by 6.372.779+6.3
- Terminal-Bench HardDeepSeek-V4-Flash by 4.531.135.6+4.5
AgentsDeepSeek-V4-Flash
- BrowseCompDeepSeek-V4-Flash by 6112.273.2+61
- GDPValDeepSeek-V4-Flash by 37.29.746.9+37.2
- τ-Bench V3 · BankingDeepSeek-V4-Flash by 22.716.739.4+22.7
ReasoningDeepSeek-V4-Flash
- ARC-AGI-2DeepSeek-V4-Flash by 55.55.961.4+55.5
- Humanity's Last ExamDeepSeek-V4-Flash by 27.910.738.6+27.9
- CritPtDeepSeek-V4-Flash by 16.30.316.6+16.3
- GPQA DiamondDeepSeek-V4-Flash by 13.177.790.8+13.1
- SimpleBenchtie45.546.3tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 62.670.98.3+62.6
- AA-Omniscience · AccuracyDeepSeek-V4-Flash by 17.722.740.4+17.7
Long documentsDeepSeek-V4-Flash
- AA-LCRDeepSeek-V4-Flash by 9.470.379.7+9.4
Following instructionsDeepSeek-V4-Flash
- IFBenchDeepSeek-V4-Flash by 24.554.779.2+24.5
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.
- ARC-AGI-1DeepSeek-V4-Flash by 494089+49
- Artificial Analysis Coding IndexDeepSeek-V4-Flash by 31.537.669.1+31.5
- τ²-Bench Telecom (AA run)DeepSeek-V4-Flash by 30.464.695+30.4
- HLE (with tools)DeepSeek-V4-Flash by 24.820.345.1+24.8
- AA Agentic IndexDeepSeek-V4-Flash by 24.117.641.7+24.1
- LiveCodeBenchDeepSeek-V4-Flash by 23.168.591.6+23.1
- AA IntelligenceDeepSeek-V4-Flash by 15.418.934.3+15.4
- AA-OmniscienceClaude Sonnet 4 by 14.50.2-14.3+14.5
- MMLU-ProDeepSeek-V4-Flash by 2.583.786.2+2.5
Questions people ask
Which is better, Claude Sonnet 4 or DeepSeek-V4-Flash?
DeepSeek-V4-Flash wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Claude Sonnet 4 wins none. They are level on facts.
Which is better for coding?
DeepSeek-V4-Flash. It wins 7 of the 7 coding tests both models report; Claude Sonnet 4 wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; DeepSeek-V4-Flash costs $0.44 and $1.32. That makes DeepSeek-V4-Flash about 90% cheaper for the same work.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 19 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.