Noometry

Model comparison

DeepSeek V4 Pro vs Qwen3.5 Max Preview

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 45.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

DeepSeek V4 Pro DeepSeek

54.3

Rank #31 Confirmed

Qwen3.5 Max Preview Alibaba (Qwen)

45.3

Rank #71 Confirmed

Summary

  • They share 17 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 4 categories and Qwen3.5 Max Preview in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 30.8.
  • DeepSeek V4 Pro has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 ProQwen3.5 Max Preview
ProviderDeepSeekAlibaba (Qwen)
Noometry Index54.345.3
Released2026-04-24—
WeightsOpenProprietary
Context window1M—
Max output393K—
Input $ / M tokens$0.66—
Output $ / M tokens$1.98—
Results tracked4817

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

Category by category

Coding DeepSeek V4 Pro leads

DeepSeek V4 Pro: 52.4 (#34), Qwen3.5 Max Preview: 44.0 (#77)

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
LMArena Coding14701487
SWE-bench Verified77.6%—
FrontierCode28.6%—
LMArena WebDev1582—
SciCode51%—
WeirdML66.2%—
ALE-Bench1,403—

Agentic & Tool Use Not comparable

DeepSeek V4 Pro: 32.8 (#58), Qwen3.5 Max Preview: —

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
APEX-Agents47.3%—
Vending-Bench 23,285—

Reasoning DeepSeek V4 Pro leads

DeepSeek V4 Pro: 56.5 (#24), Qwen3.5 Max Preview: 30.8 (#84)

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
LMArena Hard Prompts14611483
ARC-AGI-261.3%—
Kagi LLM Benchmark53.5%—
NYT Connections (extended)91.3%—
ARC-AGI-190.5%—
CritPt18%—
Chess Puzzles47%—
Mystery Game Puzzles43%—
DTBench93.9%—
LMCA45.5%—
Surface Evolver Bench40%—
Epoch Capabilities Index155.31—
ForecastBench56.1—

Math DeepSeek V4 Pro leads

DeepSeek V4 Pro: 64.8 (#30), Qwen3.5 Max Preview: 40.1 (#94)

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
LMArena Math14551474
FrontierMath (Tiers 1-3)64.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions76.6%—
OTIS Mock AIME 2024-202598.6%—
ProofBench50%—

Knowledge DeepSeek V4 Pro leads

DeepSeek V4 Pro: 59.5 (#31), Qwen3.5 Max Preview: 41.8 (#107)

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
LMArena Expert14641489
GPQA Diamond91.7%—
SimpleQA Verified52.9%—
Vectara Hallucination Rate8.6%—

Multilingual Qwen3.5 Max Preview leads

DeepSeek V4 Pro: 54.4 (#45), Qwen3.5 Max Preview: 56.2 (#22)

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
LMArena Non-English14391465
LMArena Chinese14861534
LMArena French14721484
LMArena German14581487
LMArena Japanese14451495
LMArena Korean14471438
LMArena Russian14531471
LMArena Spanish14581470

Instruction Following Too close to call

DeepSeek V4 Pro: 76.1 (#47), Qwen3.5 Max Preview: 77.0 (#31)

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
LMArena Instruction Following14481467

Long Context Too close to call

DeepSeek V4 Pro: 45.0 (#51), Qwen3.5 Max Preview: 45.2 (#45)

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
LMArena Longer Query14581476
CL-bench Life13.5%—

Writing & Preference Too close to call

DeepSeek V4 Pro: 65.5 (#46), Qwen3.5 Max Preview: 66.0 (#41)

BenchmarkDeepSeek V4 ProQwen3.5 Max Preview
LMArena Text14511470
LMArena Creative Writing14461464
LMArena Multi-Turn14671478
EQ-Bench Creative Writing1553—
EQ-Bench 41166—

Frequently asked questions

Is DeepSeek V4 Pro better than Qwen3.5 Max Preview?

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 45.3 on the Noometry Index.

Is DeepSeek V4 Pro or Qwen3.5 Max Preview better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 44.0 in the Noometry coding category.

How many benchmarks do DeepSeek V4 Pro and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen3.5 Max Preview has 17.

Related comparisons

Go deeper