DeepSeek-V4-Flash vs Qwen3.7 Plus Preview
Wins 6 of 7 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
DeepSeek-V4-Flash is the stronger all-rounder.
Scores updated · 37 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.
- MathCompetition and research-level math30DeepSeek-V4-Flash3 of 3 tests
- AgentsCarrying out multi-step tasks on its own31DeepSeek-V4-Flash3 of 4 tests
- ReasoningHard problems that need careful thinking20DeepSeek-V4-Flash2 of 3 tests · 1 tie
- CodingWriting and fixing software43DeepSeek-V4-Flash4 of 7 tests
- Long documentsFinding answers in very long texts10DeepSeek-V4-Flash1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Flash1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 79% 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-Flash pulls ahead
- Real work tasks from 44 professionsGDPVal+33.3points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+23.1points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+21.9points ahead
Where Qwen3.7 Plus Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+64points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+11.4points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+5points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Flash
- Terminal-Bench 2.1DeepSeek-V4-Flash by 17.778.761+17.7
- Terminal-Bench HardQwen3.7 Plus Preview by 11.435.647+11.4
- SWE-bench ProQwen3.7 Plus Preview by 552.657.6+5
- SciCodeDeepSeek-V4-Flash by 4.250.346.1+4.2
- SWE-bench MultilingualQwen3.7 Plus Preview by 2.573.375.8+2.5
- SWE-bench VerifiedDeepSeek-V4-Flash by 1.37977.7+1.3
- LiveCodeBench v6DeepSeek-V4-Flash by 190.689.6+1
AgentsDeepSeek-V4-Flash
- GDPValDeepSeek-V4-Flash by 33.346.713.4+33.3
- τ-Bench V3 · BankingDeepSeek-V4-Flash by 21.939.417.5+21.9
- Terminal-Bench 4.0DeepSeek-V4-Flash by 11.112.11+11.1
- MCP AtlasQwen3.7 Plus Preview by 4.26973.2+4.2
ReasoningDeepSeek-V4-Flash
- CritPtDeepSeek-V4-Flash by 7.516.69.1+7.5
- Humanity's Last ExamDeepSeek-V4-Flash by 338.635.6+3
- GPQA Diamondtie90.890tie
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.7 Plus Preview by 648.372.3+64
- AA-Omniscience · AccuracyDeepSeek-V4-Flash by 17.940.422.5+17.9
MathDeepSeek-V4-Flash
- FrontierMath Tiers 1-3 (v2)DeepSeek-V4-Flash by 23.157.534.4+23.1
- IMOAnswerBenchDeepSeek-V4-Flash by 2.488.486+2.4
- HMMT Feb. 2026DeepSeek-V4-Flash by 1.994.892.9+1.9
Following instructionsDeepSeek-V4-Flash
- IFBenchDeepSeek-V4-Flash by 1.279.278+1.2
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.
- DeepSWE 1.1DeepSeek-V4-Flash by 37.954.416.5+37.9
- AA Agentic IndexDeepSeek-V4-Flash by 2241.719.7+22
- Toolathlon VerifiedDeepSeek-V4-Flash by 19.770.350.6+19.7
- AA-OmniscienceQwen3.7 Plus Preview by 15.4-14.31.1+15.4
- JobBenchDeepSeek-V4-Flash by 13.741.327.6+13.7
- Terminal-Bench 2.0Qwen3.7 Plus Preview by 13.456.970.3+13.4
- Artificial Analysis Coding IndexDeepSeek-V4-Flash by 13.269.155.9+13.2
- NL2RepoDeepSeek-V4-Flash by 13.154.241.1+13.1
- Agents' Last ExamDeepSeek-V4-Flash by 1225.213.2+12
- Apex (Pass@1)DeepSeek-V4-Flash by 10.33322.7+10.3
- AA IntelligenceDeepSeek-V4-Flash by 9.134.325.2+9.1
- MMLU-ReduxQwen3.7 Plus Preview by 5.189.494.5+5.1
- MMLU-ProQwen3.7 Plus Preview by 2.386.288.5+2.3
- τ²-Bench Telecom (AA run)DeepSeek-V4-Flash by 29593+2
- WMT24++tie85.584.6tie
- MMLU-ProXtie85.585.4tie
Questions people ask
Which is better, DeepSeek-V4-Flash or Qwen3.7 Plus Preview?
DeepSeek-V4-Flash wins six of the seven areas where both have results: coding, agents, reasoning, math, long documents and following instructions. Qwen3.7 Plus Preview wins none. They are level on facts.
Which is better for coding?
DeepSeek-V4-Flash. It wins 4 of the 7 coding tests both models report; Qwen3.7 Plus Preview wins 3.
Which is cheaper?
DeepSeek-V4-Flash costs $0.14 per million input tokens and $0.28 per million output tokens; Qwen3.7 Plus Preview costs $0.40 and $1.60. That makes DeepSeek-V4-Flash about 79% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 21 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.