Skip to main content
BenchLM
Advertise

Model comparison

DeepSeek V4 Flash Base vs Qwen3.5 397B

Data verified

Head-to-head evidence from 5 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

N/A
No comparison
57.01/100
0 category wins2 category wins

Public leaderboard positions: DeepSeek V4 Flash Base unranked (Not scored); Qwen3.5 397B #71 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. DeepSeek V4 Flash Base and Qwen3.5 397B share 5 comparable benchmark results. 2 of 8 categories are comparable. 19 results are unique to DeepSeek V4 Flash Base; 50 to Qwen3.5 397B.

Updated July 23, 2026
Shared results
5
DeepSeek V4 Flash Base only
19
Qwen3.5 397B only
50
Comparable categories
2 / 8

Treat this as a split decision. DeepSeek V4 Flash Base makes more sense if you need the larger 1M context window; Qwen3.5 397B is the better fit if reasoning is the priority.

Confidence note. This is a partial-evidence comparison with 5 shared benchmark results across 2 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

DeepSeek V4 Flash Base and Qwen3.5 397B finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

DeepSeek V4 Flash Base gives you the larger context window at 1M, compared with 128K for Qwen3.5 397B.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for DeepSeek V4 Flash Base and Qwen3.5 397B
CategoryDeepSeek V4 Flash BaseΔQwen3.5 397B
ReasoningDeepSeek V4 Flash Base44.7Margin→ 18.5Qwen3.5 397B63.2
KnowledgeDeepSeek V4 Flash Base56.4Margin→ 0.2Qwen3.5 397B56.6
AgenticDeepSeek V4 Flash BaseNot measuredMarginNo overlapQwen3.5 397B56.5
CodingDeepSeek V4 Flash BaseNot measuredMarginNo overlapQwen3.5 397B66.5
MathDeepSeek V4 Flash BaseNot measuredMarginNo overlapQwen3.5 397B90.6
MultilingualDeepSeek V4 Flash BaseNot measuredMarginNo overlapQwen3.5 397B84.7
MultimodalDeepSeek V4 Flash BaseNot measuredMarginNo overlapQwen3.5 397B79.6
Inst. FollowingDeepSeek V4 Flash BaseNot measuredMarginNo overlapQwen3.5 397B92.6

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · DeepSeek V4 Flash BaseB · Qwen3.5 397B

  1. SuperGPQA

    Knowledge
    Source ↗
    A 46.5%B 70.4%
    Winner: Qwen3.5 397BΔ 23.9
    SuperGPQA: DeepSeek V4 Flash Base scored 46.5%; Qwen3.5 397B scored 70.4%. Qwen3.5 397B wins this benchmark.

  2. MMLU-Pro

    Knowledge
    Source ↗
    A 68.3%B 87.8%
    Winner: Qwen3.5 397BΔ 19.5
    MMLU-Pro: DeepSeek V4 Flash Base scored 68.3%; Qwen3.5 397B scored 87.8%. Qwen3.5 397B wins this benchmark.

  3. LongBench v2

    Reasoning
    Source ↗
    A 44.7%B 63.2%
    Winner: Qwen3.5 397BΔ 18.5
    LongBench v2: DeepSeek V4 Flash Base scored 44.7%; Qwen3.5 397B scored 63.2%. Qwen3.5 397B wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricDeepSeek V4 Flash BaseQwen3.5 397BComparison
Input / output priceUSD per 1M tokensDeepSeek V4 Flash BaseNot availableQwen3.5 397B$0.6 input / $3.6 outputA complete price comparison is not available.
Generation speedtokens per secondDeepSeek V4 Flash BaseNot availableQwen3.5 397B96 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenDeepSeek V4 Flash BaseNot availableQwen3.5 397B2.44 sA complete latency comparison is not available.
Context windowmaximum listed tokensDeepSeek V4 Flash Base1MQwen3.5 397B128KDeepSeek V4 Flash Base lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkDeepSeek V4 Flash BaseQwen3.5 397BResult
Terminal-Bench 2.0Source —52.5%Not comparable
BrowseCompSource —62%Not comparable
Claw-EvalSource —56.8%Not comparable
QwenClawBenchSource —51.8%Not comparable
τ³-bench resultsSource —68.4%Not comparable
VITA-BenchSource —43.7%Not comparable
DeepPlanningSource —37.6%Not comparable
ToolathlonSource —36.3%Not comparable
MCP AtlasSource —46.1%Not comparable
MCP-TasksSource —74.2%Not comparable
WideResearchSource —74.0%Not comparable
τ²-bench resultsSource —95.6%Not comparable
Gert LabsSource —46.76%Not comparable
ResearchClawBenchSource —14.2%Not comparable
AA Agentic IndexSource —19.9%Not comparable
APEX-Agents-AASource —15.3%Not comparable
GDPval-AASource —23.1%Not comparable
GDPval-AASource —962Not comparable
Coding
BenchmarkDeepSeek V4 Flash BaseQwen3.5 397BResult
BigCodeBenchSource 56.8%—Not comparable
HumanEvalSource 69.5%—Not comparable
SWE-bench VerifiedSource —76.2%Not comparable
LiveCodeBench v6Source —83.6%Not comparable
SWE-bench ProSource —50.9%Not comparable
AA-SciCodeSource —42.0%Not comparable
AA Coding IndexSource —48.2%Not comparable
ReasoningQwen3.5 397B wins
BenchmarkDeepSeek V4 Flash BaseQwen3.5 397BResult
BBHSource 86.9%—Not comparable
DROPSource 88.6%—Not comparable
HellaSwagSource 85.7%—Not comparable
WinoGrandeSource 79.5%—Not comparable
CLUEWSCSource 82.2%—Not comparable
LongBench v2Source 44.7%63.2%Qwen3.5 397B leads
AI-NeedleSource —68.7%Not comparable
AA-LCRSource —65.7%Not comparable
CritPtSource —1.7%Not comparable
KnowledgeQwen3.5 397B wins
BenchmarkDeepSeek V4 Flash BaseQwen3.5 397BResult
AGIEvalSource 82.6%—Not comparable
MMLUSource 88.7%—Not comparable
MMLU-ReduxSource 89.4%94.9%Qwen3.5 397B leads
MMLU-ProSource 68.3%87.8%Qwen3.5 397B leads
MMMLUSource 88.8%—Not comparable
C-EvalSource 92.1%93%Qwen3.5 397B leads
CMMLUSource 90.4%—Not comparable
MultiLoKoSource 42.2%—Not comparable
SimpleQASource 30.1%—Not comparable
SuperGPQASource 46.5%70.4%Qwen3.5 397B leads
FACTS ParametricSource 33.9%—Not comparable
TriviaQASource 82.8%—Not comparable
GPQASource —88.4%Not comparable
HLESource —28.7%Not comparable
Artificial Analysis Intelligence IndexSource —33.7%Not comparable
AA-GPQA DiamondSource —89.3%Not comparable
AA-HLESource —27.3%Not comparable
AA-Omniscience IndexSource —-29.8%Not comparable
AA-Omniscience AccuracySource —31.4%Not comparable
AA-Omniscience Hallucination RateSource —89.1%Not comparable
Math
BenchmarkDeepSeek V4 Flash BaseQwen3.5 397BResult
GSM8KSource 90.8%—Not comparable
MATHSource 57.4%—Not comparable
CMathSource 93.6%—Not comparable
AIME26Source —93.3%Not comparable
HMMT Feb 2025Source —94.8%Not comparable
HMMT Nov 2025Source —92.7%Not comparable
HMMT Feb 2026Source —87.9%Not comparable
MMAnswerBenchSource —80.9%Not comparable
Multilingual
BenchmarkDeepSeek V4 Flash BaseQwen3.5 397BResult
MGSMSource 85.7%—Not comparable
MMLU-ProXSource —84.7%Not comparable
NOVA-63Source —59.1%Not comparable
Multimodal
BenchmarkDeepSeek V4 Flash BaseQwen3.5 397BResult
MMMU-ProSource —79%Not comparable
MathVisionSource —88.6%Not comparable
CharXivSource —80.8%Not comparable
VideoMMMUSource —84.7%Not comparable
ScreenSpot ProSource —65.6%Not comparable
V*Source —95.8%Not comparable
AA-MMMU-ProSource —77.3%Not comparable
Inst. Following
BenchmarkDeepSeek V4 Flash BaseQwen3.5 397BResult
IFEvalSource —92.6%Not comparable
AA-IFBenchSource —78.8%Not comparable
Frequently Asked Questions (3)

Which is better, DeepSeek V4 Flash Base or Qwen3.5 397B?

DeepSeek V4 Flash Base and Qwen3.5 397B are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, DeepSeek V4 Flash Base or Qwen3.5 397B?

Qwen3.5 397B has the edge for knowledge tasks in this comparison, averaging 56.6 versus 56.4. Inside this category, SuperGPQA is the benchmark that creates the most daylight between them.

Which is better for reasoning, DeepSeek V4 Flash Base or Qwen3.5 397B?

Qwen3.5 397B has the edge for reasoning in this comparison, averaging 63.2 versus 44.7. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

DeepSeek Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.