Noometry

Model comparison

DeepSeek V4.1 Flash vs Qwen3.5 Plus

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 42.9 on the Noometry Index.

Last verified . 7 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Qwen3.5 Plus Alibaba (Qwen)

42.9

Rank #106 Confirmed

Summary

  • They share 7 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 4 categories and Qwen3.5 Plus in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 32.8.
  • The biggest single-benchmark swing is Mystery Game Puzzles: 43% for DeepSeek V4.1 Flash and 17% for Qwen3.5 Plus.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.40 / $2.40 for Qwen3.5 Plus.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 FlashQwen3.5 Plus
ProviderDeepSeekAlibaba (Qwen)
Noometry Index52.842.9
Released2026-09-092026-02-16
WeightsOpenProprietary
Context window1M1M
Max output393K66K
Input $ / M tokens$0.15$0.40
Output $ / M tokens$0.60$2.40
Results tracked3715

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

Category by category

Coding Not comparable

DeepSeek V4.1 Flash: 52.9 (#32), Qwen3.5 Plus: —

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
ALE-Bench1,092621.92
LMArena WebDev1619—
SciCode51.9%—
LMArena Coding1506—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), Qwen3.5 Plus: —

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
APEX-Agents39.5%—
GDP.pdf19.8%—
Vending-Bench 2—0.54

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Qwen3.5 Plus: 32.8 (#74)

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
Mystery Game Puzzles43%17%
DTBench89.9%80.5%
LMCA47%36.4%
Epoch Capabilities Index154.9146.78
NYT Connections (extended)89.6%—
CritPt14.3%—
Chess Puzzles—22%
LMArena Hard Prompts1483—
Surface Evolver Bench46.3%—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Qwen3.5 Plus: 49.6 (#61)

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
OTIS Mock AIME 2024-202598.3%86.7%
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
ProofBench54%—
LMArena Math1477—
FrontierMath (Feb 2025 set)—21%
FrontierMath Tier 4 (v1)—2.1%

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Qwen3.5 Plus: 46.0 (#83)

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
GPQA Diamond89.8%84.8%
SimpleQA Verified—25.4%
Vectara Hallucination Rate—10.7%
LMArena Expert1506—

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Qwen3.5 Plus: —

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual Not comparable

DeepSeek V4.1 Flash: 55.0 (#35), Qwen3.5 Plus: —

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
LMArena Non-English1448—
LMArena Chinese1497—
LMArena French1452—
LMArena German1484—
LMArena Japanese1412—
LMArena Korean1452—
LMArena Russian1471—
LMArena Spanish1459—

Instruction Following Not comparable

DeepSeek V4.1 Flash: 77.3 (#26), Qwen3.5 Plus: —

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
LMArena Instruction Following1474—

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Qwen3.5 Plus: 43.0 (#113)

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
CL-bench—19.8%
CL-bench Life—12.4%
LMArena Longer Query1475—

Writing & Preference Not comparable

DeepSeek V4.1 Flash: 65.4 (#48), Qwen3.5 Plus: —

BenchmarkDeepSeek V4.1 FlashQwen3.5 Plus
LMArena Text1462—
LMArena Creative Writing1435—
EQ-Bench Creative Writing1540—
LMArena Multi-Turn1457—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Qwen3.5 Plus?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 42.9 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or Qwen3.5 Plus?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.5 Plus lists at $0.40 and $2.40.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do DeepSeek V4.1 Flash and Qwen3.5 Plus share?

7 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Qwen3.5 Plus has 15.

Related comparisons

Go deeper