Noometry

Model comparison

DeepSeek V4 Flash vs Qwen3.7 Plus

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 45.3 on the Noometry Index.

Last verified . 29 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

Qwen3.7 Plus Alibaba (Qwen)

45.3

Rank #72 Confirmed

Summary

  • They share 29 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 4 categories and Qwen3.7 Plus in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 39.3.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 57.5% for DeepSeek V4 Flash and 34.4% for Qwen3.7 Plus.
  • DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
  • DeepSeek V4 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 FlashQwen3.7 Plus
ProviderDeepSeekAlibaba (Qwen)
Noometry Index53.645.3
Released2026-04-242026-06-02
WeightsOpenProprietary
Context window1M1M
Max output393K131K
Input $ / M tokens$0.15$0.40
Output $ / M tokens$0.60$1.60
Results tracked4132

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

Category by category

Coding DeepSeek V4 Flash leads

DeepSeek V4 Flash: 47.9 (#59), Qwen3.7 Plus: 36.6 (#206)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
FrontierCode18.8%10.2%
SciCode49.9%45.5%
LMArena Coding14571473
LMArena WebDev1582—
WeirdML63%—
ALE-Bench1,306—

Agentic & Tool Use Not comparable

DeepSeek V4 Flash: —, Qwen3.7 Plus: 21.4 (#138)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
OSWorld 2.0—2.8%

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#30), Qwen3.7 Plus: 39.3 (#59)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
NYT Connections (extended)89.6%74.8%
CritPt16.6%9.1%
Chess Puzzles33%24%
LMArena Hard Prompts14441460
Mystery Game Puzzles34%17%
DTBench90.9%84%
LMCA41.7%37.6%
Epoch Capabilities Index154.49147.37
ARC-AGI-261.4%—
SimpleBench61.1%—
Kagi LLM Benchmark52.2%—
ARC-AGI-189%—

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.3 (#37), Qwen3.7 Plus: 50.5 (#56)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
FrontierMath (Tiers 1-3)57.5%34.4%
OTIS Mock AIME 2024-202594.4%93.3%
LMArena Math14271466
FrontierMath Tier 424.4%—
MathArena Final-Answer Competitions76.5%—
ProofBench56%—

Knowledge Too close to call

DeepSeek V4 Flash: 55.4 (#48), Qwen3.7 Plus: 54.9 (#51)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
GPQA Diamond91%87.9%
LMArena Expert14411467
SimpleQA Verified33.6%—

Multimodal Not comparable

DeepSeek V4 Flash: —, Qwen3.7 Plus: 41.8 (#33)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
LMArena Vision—1279
LMArena Document—1444

Multilingual Qwen3.7 Plus leads

DeepSeek V4 Flash: 53.0 (#72), Qwen3.7 Plus: 54.8 (#38)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
LMArena Non-English14201445
LMArena Chinese14681510
LMArena French14391473
LMArena German14181471
LMArena Japanese14061413
LMArena Korean13841415
LMArena Russian14281457
LMArena Spanish14361457

Instruction Following Too close to call

DeepSeek V4 Flash: 74.9 (#81), Qwen3.7 Plus: 75.8 (#52)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
LMArena Instruction Following14211440

Long Context Too close to call

DeepSeek V4 Flash: 43.8 (#85), Qwen3.7 Plus: 44.5 (#65)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
LMArena Longer Query14341455

Writing & Preference Too close to call

DeepSeek V4 Flash: 63.8 (#61), Qwen3.7 Plus: 64.3 (#56)

BenchmarkDeepSeek V4 FlashQwen3.7 Plus
LMArena Text14321455
LMArena Creative Writing14031439
LMArena Multi-Turn14491460
EQ-Bench Creative Writing1559—

Frequently asked questions

Is DeepSeek V4 Flash better than Qwen3.7 Plus?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 45.3 on the Noometry Index.

Which is cheaper, DeepSeek V4 Flash or Qwen3.7 Plus?

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.

Is DeepSeek V4 Flash or Qwen3.7 Plus better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 36.6 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do DeepSeek V4 Flash and Qwen3.7 Plus share?

29 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Qwen3.7 Plus has 32.

Related comparisons

Go deeper