Claude Sonnet 4.5 vs DeepSeek-V3.1
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Claude Sonnet 4.5 is the stronger all-rounder.DeepSeek-V3.1 is cheaper.
Scores updated · 32 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 software40Claude Sonnet 4.54 of 4 tests
- ReasoningHard problems that need careful thinking30Claude Sonnet 4.53 of 4 tests · 1 tie
- Following instructionsDoing exactly what it is asked20Claude Sonnet 4.52 of 2 tests
- FactsGetting facts right instead of making them up21Claude Sonnet 4.52 of 3 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
Long documents rests on a single test.
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-V3.1 costs 88% 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 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+33.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.8points ahead
- Reasons across sets of long documentsAA-LCR+15.6points ahead
Where DeepSeek-V3.1 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+5.9points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- SWE-bench MultilingualClaude Sonnet 4.5 by 12.56754.5+12.5
- SWE-bench VerifiedClaude Sonnet 4.5 by 11.277.266+11.2
- Terminal-Bench HardClaude Sonnet 4.5 by 10.635.625+10.6
- SciCodeClaude Sonnet 4.5 by 6.645.739.1+6.6
AgentsEven
- GDPValClaude Sonnet 4.5 by 14.920.55.6+14.9
- BrowseCompDeepSeek-V3.1 by 5.924.130+5.9
ReasoningClaude Sonnet 4.5
- SimpleBenchClaude Sonnet 4.5 by 14.354.340+14.3
- GPQA DiamondClaude Sonnet 4.5 by 5.583.477.9+5.5
- Humanity's Last ExamClaude Sonnet 4.5 by 3.517.814.3+3.5
- CritPttie1.12tie
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 33.450.917.5+33.4
- Vectara HHEM hallucination ratelower is betterDeepSeek-V3.1 by 6.5125.5+6.5
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 3.932.929+3.9
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 15.672.356.7+15.6
Following instructionsClaude Sonnet 4.5
- IFBenchClaude Sonnet 4.5 by 15.857.341.5+15.8
- Multi-ChallengeClaude Sonnet 4.5 by 9.255.346.1+9.2
Other results16 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.
- HMMT 2025Claude Sonnet 4.5 by 41.174.633.5+41.1
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 40.778.137.4+40.7
- AIME 2025Claude Sonnet 4.5 by 37.28749.8+37.2
- AA-OmniscienceClaude Sonnet 4.5 by 29.5-0.1-29.6+29.5
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 22.452.129.7+22.4
- Terminal-BenchClaude Sonnet 4.5 by 18.75031.3+18.7
- HMMT Feb. 2025DeepSeek-V3.1 by 18.367.585.8+18.3
- LiveCodeBenchClaude Sonnet 4.5 by 14.67156.4+14.6
- AA IntelligenceClaude Sonnet 4.5 by 7.220.713.5+7.2
- BrowseComp-ZHDeepSeek-V3.1 by 6.842.449.2+6.8
- vectara_factual_consistencyDeepSeek-V3.1 by 6.58894.5+6.5
- vectara_avg_summary_lengthClaude Sonnet 4.5 by 64.1 rating points127.863.7+64.1 rating
- MMLU-ProClaude Sonnet 4.5 by 3.887.583.7+3.8
- MMLU-ReduxClaude Sonnet 4.5 by 3.895.691.8+3.8
- AA Agentic IndexDeepSeek-V3.1 by 1.417.518.9+1.4
- vectara_answer_rateClaude Sonnet 4.5 by 1.195.694.5+1.1
Questions people ask
Which is better, Claude Sonnet 4.5 or DeepSeek-V3.1?
Claude Sonnet 4.5 wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. DeepSeek-V3.1 wins none, but costs 88% less. They are level on agents.
Which is better for coding?
Claude Sonnet 4.5. It wins 4 of the 4 coding tests both models report; DeepSeek-V3.1 wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; DeepSeek-V3.1 costs $0.56 and $1.68. That makes DeepSeek-V3.1 about 88% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.