Noometry

Model comparison

DeepSeek V4.1 Flash vs Qwen3.5 397B-A17B

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 46.0 on the Noometry Index.

Last verified . 29 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Qwen3.5 397B-A17B Alibaba (Qwen)

46.0

Rank #67 Confirmed

Summary

  • They share 29 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Qwen3.5 397B-A17B in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 46.1.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 67.4% for DeepSeek V4.1 Flash and 31.2% for Qwen3.5 397B-A17B.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 262K.

Side by side

DeepSeek V4.1 FlashQwen3.5 397B-A17B
ProviderDeepSeekAlibaba (Qwen)
Noometry Index52.846.0
Released2026-09-092026-02-01
WeightsOpenOpen
Context window1M262K
Max output393K66K
Input $ / M tokens$0.15$0.60
Output $ / M tokens$0.60$3.60
Results tracked3736

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Qwen3.5 397B-A17B: 42.0 (#114)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
LMArena WebDev16191400
LMArena Coding15061465
SciCode51.9%—
ALE-Bench1,092—

Agentic & Tool Use Qwen3.5 397B-A17B leads

DeepSeek V4.1 Flash: 31.2 (#69), Qwen3.5 397B-A17B: 33.3 (#53)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
APEX-Agents39.5%24.9%
τ²-bench Airline—81.5%
τ²-bench Banking—9.8%
τ²-bench Retail—84.4%
τ²-bench Telecom—97.8%
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Qwen3.5 397B-A17B: 34.5 (#70)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
NYT Connections (extended)89.6%58.9%
LMArena Hard Prompts14831448
Mystery Game Puzzles43%18%
DTBench89.9%87.5%
LMCA47%37.9%
Epoch Capabilities Index154.9146.65
Kagi LLM Benchmark—73.7%
CritPt14.3%—
Chess Puzzles—13%
Thematic Generalization—65.1%
Surface Evolver Bench46.3%—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Qwen3.5 397B-A17B: 46.1 (#73)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
FrontierMath (Tiers 1-3)67.4%31.2%
OTIS Mock AIME 2024-202598.3%88.9%
LMArena Math14771454
FrontierMath Tier 426.8%—
ProofBench54%—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Qwen3.5 397B-A17B: 53.3 (#58)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
GPQA Diamond89.8%86.4%
LMArena Expert15061462

Multimodal Qwen3.5 397B-A17B leads

DeepSeek V4.1 Flash: 39.1 (#61), Qwen3.5 397B-A17B: 40.7 (#44)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
LMArena Vision12771263
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Qwen3.5 397B-A17B: 53.7 (#59)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
LMArena Non-English14481430
LMArena Chinese14971500
LMArena French14521461
LMArena German14841447
LMArena Japanese14121426
LMArena Korean14521384
LMArena Russian14711429
LMArena Spanish14591441

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Qwen3.5 397B-A17B: 75.0 (#77)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
LMArena Instruction Following14741424

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Qwen3.5 397B-A17B: 44.1 (#74)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
LMArena Longer Query14751442

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Qwen3.5 397B-A17B: 62.3 (#79)

BenchmarkDeepSeek V4.1 FlashQwen3.5 397B-A17B
LMArena Text14621438
LMArena Creative Writing14351401
EQ-Bench Creative Writing15401478
LMArena Multi-Turn14571446

Frequently asked questions

Is DeepSeek V4.1 Flash better than Qwen3.5 397B-A17B?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 46.0 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Qwen3.5 397B-A17B?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.

Is DeepSeek V4.1 Flash or Qwen3.5 397B-A17B better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 42.0 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 262K.

How many benchmarks do DeepSeek V4.1 Flash and Qwen3.5 397B-A17B share?

29 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Qwen3.5 397B-A17B has 36.

Related comparisons

Go deeper