Claude Opus 4 vs DeepSeek-V4-Pro
Wins 0 of 5 areas
—
Wins 5 of 5 areas
Coding · Reasoning · Facts · Long documents · Following instructions
DeepSeek-V4-Pro is the stronger all-rounder.
Scores updated · 22 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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 software04DeepSeek-V4-Pro4 of 4 tests
- ReasoningHard problems that need careful thinking12DeepSeek-V4-Pro2 of 3 tests
- FactsGetting facts right instead of making them up01DeepSeek-V4-Pro1 of 1 test
- Long documentsFinding answers in very long texts01DeepSeek-V4-Pro1 of 1 test
- Following instructionsDoing exactly what it is asked01DeepSeek-V4-Pro1 of 1 test
Facts, 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 94% 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
- Recent programming contest problemsLiveCodeBench v6+45.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+25.2points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+22.8points ahead
Where Claude Opus 4 pulls ahead
- Common-sense trick questionsSimpleBench+7.9points ahead
Every test, side by side
All 22 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 45.147.492.5+45.1
- Terminal-Bench HardDeepSeek-V4-Pro by 15.131.146.2+15.1
- SciCodeDeepSeek-V4-Pro by 1139.850.8+11
- SWE-bench VerifiedDeepSeek-V4-Pro by 8.172.580.6+8.1
ReasoningDeepSeek-V4-Pro
- Humanity's Last ExamDeepSeek-V4-Pro by 25.212.337.5+25.2
- GPQA DiamondDeepSeek-V4-Pro by 9.279.688.8+9.2
- SimpleBenchClaude Opus 4 by 7.958.850.9+7.9
FactsDeepSeek-V4-Pro
- Vectara HHEM hallucination ratelower is betterDeepSeek-V4-Pro by 3.4128.6+3.4
Following instructionsDeepSeek-V4-Pro
- IFBenchDeepSeek-V4-Pro by 22.853.776.5+22.8
Other results12 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 35.122.857.9+35.1
- Artificial Analysis Coding IndexDeepSeek-V4-Pro by 25.43459.4+25.4
- LiveCodeBenchDeepSeek-V4-Pro by 23.170.493.5+23.1
- τ²-Bench Telecom (AA run)DeepSeek-V4-Pro by 22.873.496.2+22.8
- AA IntelligenceDeepSeek-V4-Pro by 9.820.630.4+9.8
- vectara_answer_rateDeepSeek-V4-Pro by 6.29197.2+6.2
- MMLU-ReduxClaude Opus 4 by 3.494.290.8+3.4
- vectara_factual_consistencyDeepSeek-V4-Pro by 3.48891.4+3.4
- vectara_avg_summary_lengthDeepSeek-V4-Pro by 30.6 rating points123.2153.8+30.6 rating
- MMLUClaude Opus 4 by 2.892.990.1+2.8
- LiveBenchClaude Opus 4 by 174.673.6+1
- MMLU-Protie86.687.5tie
Questions people ask
Which is better, Claude Opus 4 or DeepSeek-V4-Pro?
DeepSeek-V4-Pro wins all five areas where both have results: coding, reasoning, facts, long documents and following instructions. Claude Opus 4 wins none.
Which is better for coding?
DeepSeek-V4-Pro. It wins 4 of the 4 coding tests both models report; Claude Opus 4 wins none.
Which is cheaper?
Claude Opus 4 costs $15.00 per million input tokens and $75.00 per million output tokens; DeepSeek-V4-Pro costs $1.32 and $3.96. That makes DeepSeek-V4-Pro about 94% cheaper for the same work.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.