Claude Sonnet 5 vs DeepSeek-V4-Pro
Wins 6 of 7 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Wins 1 of 7 areas
Facts
Claude Sonnet 5 is the stronger all-rounder.DeepSeek-V4-Pro is cheaper and better at facts.
Scores updated · 40 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 software80Claude Sonnet 58 of 8 tests
- ReasoningHard problems that need careful thinking50Claude Sonnet 55 of 5 tests
- MathCompetition and research-level math40Claude Sonnet 54 of 4 tests
- AgentsCarrying out multi-step tasks on its own30Claude Sonnet 53 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Sonnet 51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Sonnet 51 of 1 test
- FactsGetting facts right instead of making them up12DeepSeek-V4-Pro2 of 3 tests
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 89% 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 Claude Sonnet 5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+54.7points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+26.9points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+20.3points ahead
Where DeepSeek-V4-Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+12.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2.9points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 5
- LiveBench · Agentic CodingClaude Sonnet 5 by 16.859.442.6+16.8
- Terminal-Bench 2.1Claude Sonnet 5 by 16.580.564+16.5
- LiveBench · CodingClaude Sonnet 5 by 10.780.770+10.7
- SWE-bench ProClaude Sonnet 5 by 7.863.255.4+7.8
- LMArena · WebDevClaude Sonnet 5 by 76 rating points15391463+76 rating
- SWE-bench VerifiedClaude Sonnet 5 by 4.685.280.6+4.6
- SciCodeClaude Sonnet 5 by 3.554.350.8+3.5
- SWE-bench MultilingualClaude Sonnet 5 by 2.178.376.2+2.1
AgentsClaude Sonnet 5
- GDPValClaude Sonnet 5 by 15.448.332.9+15.4
- τ-Bench V3 · BankingClaude Sonnet 5 by 7.237.330.1+7.2
- BrowseCompClaude Sonnet 5 by 1.384.783.4+1.3
- Terminal-Bench 4.0tie14.114.6tie
ReasoningClaude Sonnet 5
- SimpleBenchClaude Sonnet 5 by 9.760.650.9+9.7
- LiveBench · ReasoningClaude Sonnet 5 by 688.782.7+6
- CritPtClaude Sonnet 5 by 416.912.9+4
- Humanity's Last ExamClaude Sonnet 5 by 3.841.337.5+3.8
- GPQA DiamondClaude Sonnet 5 by 2.391.188.8+2.3
FactsDeepSeek-V4-Pro
- AA-Omniscience · Non-hallucinationClaude Sonnet 5 by 54.760.65.9+54.7
- SimpleQA VerifiedDeepSeek-V4-Pro by 12.533.746.2+12.5
- AA-Omniscience · AccuracyDeepSeek-V4-Pro by 2.94043+2.9
MathClaude Sonnet 5
- FrontierMath Tier 4Claude Sonnet 5 by 26.929.32.4+26.9
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 5 by 20.365.645.3+20.3
- USAMO 2026Claude Sonnet 5 by 18.879.560.7+18.8
- LiveBench · MathematicsClaude Sonnet 5 by 2.292.990.7+2.2
Following instructionsClaude Sonnet 5
- LiveBench · Instruction FollowingClaude Sonnet 5 by 1.563.962.4+1.5
Other results14 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.
- GDPval-AA v2Claude Sonnet 5 by 312 rating points16181306+312 rating
- Program BenchClaude Sonnet 5 by 29.577.347.8+29.5
- AA-OmniscienceClaude Sonnet 5 by 27.216.4-10.7+27.2
- Toolathlon VerifiedClaude Sonnet 5 by 18.874.755.9+18.8
- AA Agentic IndexClaude Sonnet 5 by 16.644.327.7+16.6
- Terminal-Bench 2.0Claude Sonnet 5 by 12.580.467.9+12.5
- Artificial Analysis Coding IndexClaude Sonnet 5 by 12.171.559.4+12.1
- AA IntelligenceClaude Sonnet 5 by 7.838.230.4+7.8
- livebench_languageDeepSeek-V4-Pro by 3.17578.1+3.1
- livebench_data_analysisDeepSeek-V4-Pro by 2.871.774.5+2.8
- Terminal-bench 3.0Claude Sonnet 5 by 2.814.611.8+2.8
- HLE (with tools)DeepSeek-V4-Pro by 2.657.460+2.6
- ToolathlonClaude Sonnet 5 by 2.554.351.8+2.5
- Terminal-Bench 4.0tie12.412.4tie
Questions people ask
Which is better, Claude Sonnet 5 or DeepSeek-V4-Pro?
Claude Sonnet 5 wins six of the seven areas where both have results: coding, agents, reasoning, math, long documents and following instructions. DeepSeek-V4-Pro wins facts, and costs 89% less.
Which is better for coding?
Claude Sonnet 5. It wins 8 of the 8 coding tests both models report; DeepSeek-V4-Pro wins none.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; DeepSeek-V4-Pro costs $0.43 and $0.87. That makes DeepSeek-V4-Pro about 89% cheaper for the same work.
How do you compare the two?
We use the 40 benchmark tests both models have published scores on. The verdict counts the 26 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.