Noometry

Model comparison

DeepSeek V4 Flash vs Qwen2.5-Max

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 40.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek V4 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 reasoning, where DeepSeek V4 Flash leads 53.7 to 25.6.
  • DeepSeek V4 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 FlashQwen2.5-Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index53.640.7
Released2026-04-242025-01-25
WeightsOpenProprietary
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked4127

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

BenchmarkDeepSeek V4 FlashQwen2.5-Max
LMArena Coding14571359
FrontierCode18.8%—
LMArena WebDev1582—
SciCode49.9%—
WeirdML63%—
LiveBench Coding—64.4%
ALE-Bench1,306—

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#30), Qwen2.5-Max: 25.6 (#147)

BenchmarkDeepSeek V4 FlashQwen2.5-Max
LMArena Hard Prompts14441360
Epoch Capabilities Index154.49132.53
ARC-AGI-261.4%—
SimpleBench61.1%—
Kagi LLM Benchmark52.2%—
NYT Connections (extended)89.6%—
ARC-AGI-189%—
CritPt16.6%—
Chess Puzzles33%—
LiveBench Reasoning—51.4%
Mystery Game Puzzles34%—
DTBench90.9%—
LiveBench Data Analysis—67.9%
LMCA41.7%—
LiveBench—62.3%

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.3 (#37), Qwen2.5-Max: 36.9 (#162)

BenchmarkDeepSeek V4 FlashQwen2.5-Max
LMArena Math14271369
FrontierMath (Tiers 1-3)57.5%—
FrontierMath Tier 424.4%—
MathArena Final-Answer Competitions76.5%—
OTIS Mock AIME 2024-202594.4%—
ProofBench56%—
LiveBench Math—58.4%

Knowledge DeepSeek V4 Flash leads

DeepSeek V4 Flash: 55.4 (#48), Qwen2.5-Max: 35.3 (#186)

BenchmarkDeepSeek V4 FlashQwen2.5-Max
LMArena Expert14411337
GPQA Diamond91%—
SimpleQA Verified33.6%—
Confabulations—21.8%

Multilingual DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.0 (#72), Qwen2.5-Max: 48.1 (#146)

BenchmarkDeepSeek V4 FlashQwen2.5-Max
LMArena Non-English14201352
LMArena Chinese14681382
LMArena French14391396
LMArena German14181350
LMArena Japanese14061300
LMArena Korean13841304
LMArena Russian14281353
LMArena Spanish14361377

Instruction Following DeepSeek V4 Flash leads

DeepSeek V4 Flash: 74.9 (#81), Qwen2.5-Max: 71.3 (#152)

BenchmarkDeepSeek V4 FlashQwen2.5-Max
LMArena Instruction Following14211335
LiveBench Instruction Following—75.3%

Long Context DeepSeek V4 Flash leads

DeepSeek V4 Flash: 43.8 (#85), Qwen2.5-Max: 41.4 (#142)

BenchmarkDeepSeek V4 FlashQwen2.5-Max
LMArena Longer Query14341358

Writing & Preference DeepSeek V4 Flash leads

DeepSeek V4 Flash: 63.8 (#61), Qwen2.5-Max: 55.4 (#146)

BenchmarkDeepSeek V4 FlashQwen2.5-Max
LMArena Text14321367
LMArena Creative Writing14031339
LMArena Multi-Turn14491364
Short-Story Creative Writing—72.9%
EQ-Bench Creative Writing1559—
LiveBench Language—56.3%

Frequently asked questions

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

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 40.7 on the Noometry Index.

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

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 41.8 in the Noometry coding category.

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

18 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper