Claude Opus 4.7 vs DeepSeek-V4.1-Flash
Wins 2 of 8 areas
Facts · Images and charts
Wins 6 of 8 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
DeepSeek-V4.1-Flash is the stronger all-rounder.Claude Opus 4.7 is better at facts.
Scores updated · 36 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.
- ReasoningHard problems that need careful thinking13DeepSeek-V4.1-Flash3 of 7 tests · 3 ties
- MathCompetition and research-level math02DeepSeek-V4.1-Flash2 of 3 tests · 1 tie
- CodingWriting and fixing software23DeepSeek-V4.1-Flash3 of 5 tests
- AgentsCarrying out multi-step tasks on its own01DeepSeek-V4.1-Flash1 of 2 tests · 1 tie
- 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
- FactsGetting facts right instead of making them up30Claude Opus 4.73 of 3 tests
- Images and chartsUnderstanding pictures, charts and video30Claude Opus 4.73 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-V4.1-Flash costs 95% 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+26.6points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+14.6points ahead
- Real work tasks from 44 professionsGDPVal+12.4points ahead
Where Claude Opus 4.7 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+54.2points ahead
- Reasoning about charts from research papersCharXiv (RQ)+22points ahead
- Short factual questions, answered correctlySimpleQA Verified+8.8points ahead
Every test, side by side
All 36 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 26.650.777.3+26.6
- Terminal-Bench 2.1DeepSeek-V4.1-Flash by 7.583.190.6+7.5
- LMArena · WebDevDeepSeek-V4.1-Flash by 61 rating points15581619+61 rating
- SciCodeClaude Opus 4.7 by 2.654.551.9+2.6
- LiveBench · CodingClaude Opus 4.7 by 2.182.180+2.1
AgentsDeepSeek-V4.1-Flash
- GDPValDeepSeek-V4.1-Flash by 12.442.655+12.4
- AA IT-Bench SREtie46.746.9tie
ReasoningDeepSeek-V4.1-Flash
- SimpleBenchDeepSeek-V4.1-Flash by 561.766.7+5
- Humanity's Last ExamClaude Opus 4.7 by 3.142.339.2+3.1
- ARC-AGI-2DeepSeek-V4.1-Flash by 2.375.878.1+2.3
- CritPtDeepSeek-V4.1-Flash by 2.31214.3+2.3
- GPQA Diamondtie91.490.9tie
- LiveBench · Reasoningtie87.286.7tie
- ARC-AGI-3tie0.20.2tie
FactsClaude Opus 4.7
- AA-Omniscience · Non-hallucinationClaude Opus 4.7 by 54.257.73.5+54.2
- SimpleQA VerifiedClaude Opus 4.7 by 8.851.742.9+8.8
- AA-Omniscience · AccuracyClaude Opus 4.7 by 2.548.946.4+2.5
Images and chartsClaude Opus 4.7
- CharXiv (RQ)Claude Opus 4.7 by 229169+22
- LMArena · VisionClaude Opus 4.7 by 35 rating points13131278+35 rating
- MMMU-ProClaude Opus 4.7 by 1.878.877+1.8
MathDeepSeek-V4.1-Flash
- FrontierMath Tier 4DeepSeek-V4.1-Flash by 14.631.746.3+14.6
- FrontierMath Tiers 1-3 (v2)DeepSeek-V4.1-Flash by 170.271.2+1
- LiveBench · Mathematicstie92.893.3tie
Long documentsDeepSeek-V4.1-Flash
- AA-LCRDeepSeek-V4.1-Flash by 5.378.784+5.3
Following instructionsDeepSeek-V4.1-Flash
- LiveBench · Instruction FollowingDeepSeek-V4.1-Flash by 3.366.770+3.3
Other results11 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.
- BabyVisionDeepSeek-V4.1-Flash by 67.422.289.6+67.4
- AA-OmniscienceClaude Opus 4.7 by 32.627.3-5.3+32.6
- CyberGymDeepSeek-V4.1-Flash by 1573.188.1+15
- HLE (with tools)DeepSeek-V4.1-Flash by 9.254.763.9+9.2
- vectara_factual_consistencyDeepSeek-V4.1-Flash by 7.88895.8+7.8
- vectara_avg_summary_lengthClaude Opus 4.7 by 40.9 rating points149.1108.2+40.9 rating
- livebench_languageDeepSeek-V4.1-Flash by 3.377.981.2+3.3
- vectara_answer_rateDeepSeek-V4.1-Flash by 1.99899.9+1.9
- ARC-AGI-1DeepSeek-V4.1-Flash by 1.59293.5+1.5
- AA IntelligenceClaude Opus 4.7 by 1.240.739.5+1.2
- livebench_data_analysisDeepSeek-V4.1-Flash by 178.379.3+1
Questions people ask
Which is better, Claude Opus 4.7 or DeepSeek-V4.1-Flash?
DeepSeek-V4.1-Flash wins six of the eight areas we test: coding, agents, reasoning, math, long documents and following instructions. Claude Opus 4.7 wins facts 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 Opus 4.7 wins 2.
Which is cheaper?
Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; DeepSeek-V4.1-Flash costs $0.30 and $1.20. That makes DeepSeek-V4.1-Flash about 95% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 25 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.