Claude Sonnet 4 vs DeepSeek-V4-Pro
Wins 0 of 6 areas
—
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
DeepSeek-V4-Pro is the stronger all-rounder.
Scores updated · 34 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-Pro7 of 7 tests
- ReasoningHard problems that need careful thinking04DeepSeek-V4-Pro4 of 4 tests
- AgentsCarrying out multi-step tasks on its own03DeepSeek-V4-Pro3 of 3 tests
- FactsGetting facts right instead of making them up12DeepSeek-V4-Pro2 of 3 tests
- Long documentsFinding answers in very long texts01DeepSeek-V4-Pro1 of 1 test
- Following instructionsDoing exactly what it is asked01DeepSeek-V4-Pro1 of 1 test
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-Pro costs 71% 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-Pro pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+71.2points ahead
- Recent programming contest problemsLiveCodeBench v6+44points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+27.7points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+65points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Pro
- LiveCodeBench v6DeepSeek-V4-Pro by 4448.592.5+44
- Terminal-Bench 2.1DeepSeek-V4-Pro by 27.736.364+27.7
- SWE-bench MultilingualDeepSeek-V4-Pro by 19.356.976.2+19.3
- Terminal-Bench HardDeepSeek-V4-Pro by 15.131.146.2+15.1
- SWE-bench ProDeepSeek-V4-Pro by 12.742.755.4+12.7
- SciCodeDeepSeek-V4-Pro by 10.84050.8+10.8
- SWE-bench VerifiedDeepSeek-V4-Pro by 7.972.780.6+7.9
AgentsDeepSeek-V4-Pro
- BrowseCompDeepSeek-V4-Pro by 71.212.283.4+71.2
- GDPValDeepSeek-V4-Pro by 23.29.632.8+23.2
- τ-Bench V3 · BankingDeepSeek-V4-Pro by 13.416.730.1+13.4
ReasoningDeepSeek-V4-Pro
- Humanity's Last ExamDeepSeek-V4-Pro by 26.810.737.5+26.8
- CritPtDeepSeek-V4-Pro by 12.60.312.9+12.6
- GPQA DiamondDeepSeek-V4-Pro by 11.177.788.8+11.1
- SimpleBenchDeepSeek-V4-Pro by 5.445.550.9+5.4
FactsDeepSeek-V4-Pro
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 6570.95.9+65
- AA-Omniscience · AccuracyDeepSeek-V4-Pro by 20.322.743+20.3
- Vectara HHEM hallucination ratelower is betterDeepSeek-V4-Pro by 1.710.38.6+1.7
Following instructionsDeepSeek-V4-Pro
- IFBenchDeepSeek-V4-Pro by 21.854.776.5+21.8
Other results15 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-V4-Pro by 4215.957.9+42
- HLE (with tools)DeepSeek-V4-Pro by 39.720.360+39.7
- τ²-Bench Telecom (AA run)DeepSeek-V4-Pro by 31.664.696.2+31.6
- LiveCodeBenchDeepSeek-V4-Pro by 2568.593.5+25
- Artificial Analysis Coding IndexDeepSeek-V4-Pro by 21.837.659.4+21.8
- AA IntelligenceDeepSeek-V4-Pro by 11.518.930.4+11.5
- AA-OmniscienceClaude Sonnet 4 by 10.90.2-10.7+10.9
- AA Agentic IndexDeepSeek-V4-Pro by 10.117.627.7+10.1
- MMLU-ProDeepSeek-V4-Pro by 3.883.787.5+3.8
- MMLU-ReduxClaude Sonnet 4 by 2.893.690.8+2.8
- vectara_factual_consistencyDeepSeek-V4-Pro by 1.789.791.4+1.7
- MMLUClaude Sonnet 4 by 1.491.590.1+1.4
- vectara_answer_rateClaude Sonnet 4 by 1.498.697.2+1.4
- LiveBenchClaude Sonnet 4 by 1.274.873.6+1.2
- vectara_avg_summary_lengthtie145.8153.8tie
Questions people ask
Which is better, Claude Sonnet 4 or DeepSeek-V4-Pro?
DeepSeek-V4-Pro wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Claude Sonnet 4 wins none.
Which is better for coding?
DeepSeek-V4-Pro. 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-Pro costs $1.32 and $3.96. That makes DeepSeek-V4-Pro about 71% cheaper for the same work.
How do you compare the two?
We use the 34 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 15 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.