Claude 3.7 Sonnet vs DeepSeek-V4-Flash
Wins 0 of 6 areas
—
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
DeepSeek-V4-Flash is the stronger all-rounder.
Scores updated · 18 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.
- ReasoningHard problems that need careful thinking03DeepSeek-V4-Flash3 of 4 tests · 1 tie
- CodingWriting and fixing software03DeepSeek-V4-Flash3 of 3 tests
- AgentsCarrying out multi-step tasks on its own01DeepSeek-V4-Flash1 of 1 test
- Long documentsFinding answers in very long texts01DeepSeek-V4-Flash1 of 1 test
- Following instructionsDoing exactly what it is asked01DeepSeek-V4-Flash1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents, 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-Flash costs 98% 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-Flash pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+30.9points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+28.9points ahead
- Reasons across sets of long documentsAA-LCR+28points ahead
Where Claude 3.7 Sonnet pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+51.7points ahead
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Flash
- Terminal-Bench HardDeepSeek-V4-Flash by 14.421.235.6+14.4
- SciCodeDeepSeek-V4-Flash by 1040.350.3+10
- SWE-bench VerifiedDeepSeek-V4-Flash by 8.770.379+8.7
ReasoningDeepSeek-V4-Flash
- Humanity's Last ExamDeepSeek-V4-Flash by 28.99.738.6+28.9
- CritPtDeepSeek-V4-Flash by 15.70.916.6+15.7
- GPQA DiamondDeepSeek-V4-Flash by 13.677.290.8+13.6
- SimpleBenchtie46.446.3tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.7 Sonnet by 51.7608.3+51.7
- AA-Omniscience · AccuracyDeepSeek-V4-Flash by 12.42840.4+12.4
Following instructionsDeepSeek-V4-Flash
- IFBenchDeepSeek-V4-Flash by 30.948.379.2+30.9
Other results6 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.
- ARC-AGI-1DeepSeek-V4-Flash by 60.428.689+60.4
- τ²-Bench Telecom (AA run)DeepSeek-V4-Flash by 40.354.795+40.3
- Artificial Analysis Coding IndexDeepSeek-V4-Flash by 32.736.469.1+32.7
- AA IntelligenceDeepSeek-V4-Flash by 16.617.734.3+16.6
- AA-OmniscienceClaude 3.7 Sonnet by 13.6-0.7-14.3+13.6
- AA Agentic IndexDeepSeek-V4-Flash by 4.73741.7+4.7
Questions people ask
Which is better, Claude 3.7 Sonnet or DeepSeek-V4-Flash?
DeepSeek-V4-Flash wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Claude 3.7 Sonnet wins none. They are level on facts.
Which is better for coding?
DeepSeek-V4-Flash. It wins 3 of the 3 coding tests both models report; Claude 3.7 Sonnet wins none.
Which is cheaper?
Claude 3.7 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens; DeepSeek-V4-Flash costs $0.14 and $0.28. That makes DeepSeek-V4-Flash about 98% cheaper for the same work.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.