Noometry

Model comparison

DeepSeek V4.1 Flash vs Qwen2.5-Max

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 40.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 36.9.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 FlashQwen2.5-Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index52.840.7
Released2026-09-092025-01-25
WeightsOpenProprietary
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3727

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), Qwen2.5-Max: 41.8 (#117)

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Coding15061359
LMArena WebDev1619—
SciCode51.9%—
LiveBench Coding—64.4%
ALE-Bench1,092—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), Qwen2.5-Max: —

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
APEX-Agents39.5%—
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Qwen2.5-Max: 25.6 (#147)

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Hard Prompts14831360
Epoch Capabilities Index154.9132.53
NYT Connections (extended)89.6%—
CritPt14.3%—
LiveBench Reasoning—51.4%
Mystery Game Puzzles43%—
DTBench89.9%—
LiveBench Data Analysis—67.9%
LMCA47%—
Surface Evolver Bench46.3%—
LiveBench—62.3%

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Qwen2.5-Max: 36.9 (#162)

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Math14771369
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—
LiveBench Math—58.4%

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Qwen2.5-Max: 35.3 (#186)

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Expert15061337
GPQA Diamond89.8%—
Confabulations—21.8%

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Qwen2.5-Max: —

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Qwen2.5-Max: 48.1 (#146)

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Non-English14481352
LMArena Chinese14971382
LMArena French14521396
LMArena German14841350
LMArena Japanese14121300
LMArena Korean14521304
LMArena Russian14711353
LMArena Spanish14591377

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Qwen2.5-Max: 71.3 (#152)

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Instruction Following14741335
LiveBench Instruction Following—75.3%

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Qwen2.5-Max: 41.4 (#142)

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Longer Query14751358

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Qwen2.5-Max: 55.4 (#146)

BenchmarkDeepSeek V4.1 FlashQwen2.5-Max
LMArena Text14621367
LMArena Creative Writing14351339
LMArena Multi-Turn14571364
Short-Story Creative Writing—72.9%
EQ-Bench Creative Writing1540—
LiveBench Language—56.3%

Frequently asked questions

Is DeepSeek V4.1 Flash better than Qwen2.5-Max?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 40.7 on the Noometry Index.

Is DeepSeek V4.1 Flash or Qwen2.5-Max better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 41.8 in the Noometry coding category.

How many benchmarks do DeepSeek V4.1 Flash and Qwen2.5-Max share?

18 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper