Claude Sonnet 5 vs DeepSeek-V4.1-Flash
Wins 2 of 8 areas
Reasoning · Images and charts
Wins 6 of 8 areas
Coding · Agents · Facts · Math · Long documents · Following instructions
DeepSeek-V4.1-Flash is the stronger all-rounder.Claude Sonnet 5 is better at reasoning.
Scores updated · 33 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 software13DeepSeek-V4.1-Flash3 of 5 tests · 1 tie
- MathCompetition and research-level math02DeepSeek-V4.1-Flash2 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own02DeepSeek-V4.1-Flash2 of 2 tests
- FactsGetting facts right instead of making them up12DeepSeek-V4.1-Flash2 of 3 tests
- Long documentsFinding answers in very long texts01DeepSeek-V4.1-Flash1 of 1 test
- Following instructionsDoing exactly what it is asked01DeepSeek-V4.1-Flash1 of 1 test
- ReasoningHard problems that need careful thinking31Claude Sonnet 53 of 5 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Claude Sonnet 51 of 3 tests · 2 ties
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-V4.1-Flash costs 88% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where DeepSeek-V4.1-Flash pulls ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+17.9points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+17points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+12.7points ahead
Where Claude Sonnet 5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+57.1points ahead
- Reasoning about charts from research papersCharXiv (RQ)+19.3points ahead
- Research-level physics problemsCritPt+2.6points ahead
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4.1-Flash
- LiveBench · Agentic CodingDeepSeek-V4.1-Flash by 17.959.477.3+17.9
- Terminal-Bench 2.1DeepSeek-V4.1-Flash by 10.180.590.6+10.1
- LMArena · WebDevDeepSeek-V4.1-Flash by 79 rating points15401619+79 rating
- SciCodeClaude Sonnet 5 by 2.454.351.9+2.4
- LiveBench · Codingtie80.780tie
AgentsDeepSeek-V4.1-Flash
- Terminal-Bench 4.0DeepSeek-V4.1-Flash by 12.714.126.8+12.7
- GDPValDeepSeek-V4.1-Flash by 6.848.255+6.8
ReasoningClaude Sonnet 5
- SimpleBenchDeepSeek-V4.1-Flash by 6.160.666.7+6.1
- CritPtClaude Sonnet 5 by 2.616.914.3+2.6
- Humanity's Last ExamClaude Sonnet 5 by 2.141.339.2+2.1
- LiveBench · ReasoningClaude Sonnet 5 by 288.786.7+2
- GPQA Diamondtie91.190.9tie
FactsDeepSeek-V4.1-Flash
- AA-Omniscience · Non-hallucinationClaude Sonnet 5 by 57.160.63.5+57.1
- SimpleQA VerifiedDeepSeek-V4.1-Flash by 9.233.742.9+9.2
- AA-Omniscience · AccuracyDeepSeek-V4.1-Flash by 6.34046.4+6.3
Images and chartsClaude Sonnet 5
- CharXiv (RQ)Claude Sonnet 5 by 19.388.369+19.3
- LMArena · Visiontie12731278tie
- MMMU-Protie77.377tie
MathDeepSeek-V4.1-Flash
- FrontierMath Tier 4DeepSeek-V4.1-Flash by 1729.346.3+17
- FrontierMath Tiers 1-3 (v2)DeepSeek-V4.1-Flash by 5.665.671.2+5.6
- LiveBench · Mathematicstie92.993.3tie
Following instructionsDeepSeek-V4.1-Flash
- LiveBench · Instruction FollowingDeepSeek-V4.1-Flash by 6.163.970+6.1
Other results10 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.
- GDP (Surge AI)Claude Sonnet 5 by 64.481.617.2+64.4
- Program BenchClaude Sonnet 5 by 5777.320.3+57
- AA-OmniscienceClaude Sonnet 5 by 21.816.4-5.3+21.8
- DeepSWE 1.1DeepSeek-V4.1-Flash by 20.25474.2+20.2
- Terminal-Bench 4.0DeepSeek-V4.1-Flash by 18.812.431.2+18.8
- Terminal-bench 3.0DeepSeek-V4.1-Flash by 15.414.630+15.4
- livebench_data_analysisDeepSeek-V4.1-Flash by 7.671.779.3+7.6
- HLE (with tools)DeepSeek-V4.1-Flash by 6.557.463.9+6.5
- livebench_languageDeepSeek-V4.1-Flash by 6.27581.2+6.2
- AA IntelligenceDeepSeek-V4.1-Flash by 1.338.239.5+1.3
Questions people ask
Which is better, Claude Sonnet 5 or DeepSeek-V4.1-Flash?
DeepSeek-V4.1-Flash wins six of the eight areas we test: coding, agents, facts, math, long documents and following instructions. Claude Sonnet 5 wins reasoning and images and charts.
Which is better for coding?
DeepSeek-V4.1-Flash. It wins 3 of the 5 coding tests both models report; Claude Sonnet 5 wins 1, and 1 is a tie.
Which is cheaper?
Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; DeepSeek-V4.1-Flash costs $0.30 and $1.20. That makes DeepSeek-V4.1-Flash about 88% cheaper for the same work.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.