Noometry

Model comparison

DeepSeek V4 Pro vs Qwen3.7 Max

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 51.5 on the Noometry Index.

Last verified . 30 shared benchmarks.

DeepSeek V4 Pro DeepSeek

54.3

Rank #31 Confirmed

Qwen3.7 Max Alibaba (Qwen)

51.5

Rank #42 Confirmed

Summary

  • They share 30 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 5 categories and Qwen3.7 Max in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where DeepSeek V4 Pro leads 32.8 to 22.1.
  • The biggest single-benchmark swing is Chess Puzzles: 47% for DeepSeek V4 Pro and 19% for Qwen3.7 Max.
  • DeepSeek V4 Pro is cheaper at $0.66 / $1.98 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
  • DeepSeek V4 Pro has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 ProQwen3.7 Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index54.351.5
Released2026-04-242026-05-19
WeightsOpenProprietary
Context window1M1M
Max output393K131K
Input $ / M tokens$0.66$2.50
Output $ / M tokens$1.98$7.50
Results tracked4833

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), Qwen3.7 Max: 50.4 (#45)

BenchmarkDeepSeek V4 ProQwen3.7 Max
SWE-bench Verified77.6%77.3%
LMArena WebDev15821515
SciCode51%48.8%
LMArena Coding14701498
ALE-Bench1,4031,189
FrontierCode28.6%—
WeirdML66.2%—

Agentic & Tool Use DeepSeek V4 Pro leads

DeepSeek V4 Pro: 32.8 (#58), Qwen3.7 Max: 22.1 (#135)

BenchmarkDeepSeek V4 ProQwen3.7 Max
APEX-Agents47.3%—
GBAEval—0.4%
Vending-Bench 23,285—

Reasoning DeepSeek V4 Pro leads

DeepSeek V4 Pro: 56.5 (#24), Qwen3.7 Max: 49.2 (#38)

BenchmarkDeepSeek V4 ProQwen3.7 Max
NYT Connections (extended)91.3%85.1%
CritPt18%13.4%
Chess Puzzles47%19%
LMArena Hard Prompts14611483
Mystery Game Puzzles43%32%
DTBench93.9%92.3%
LMCA45.5%44%
Epoch Capabilities Index155.31153.68
ARC-AGI-261.3%—
SimpleBench—70.4%
Kagi LLM Benchmark53.5%—
ARC-AGI-190.5%—
EBR-Bench—9.5%
Surface Evolver Bench40%—
ForecastBench56.1—

Math DeepSeek V4 Pro leads

DeepSeek V4 Pro: 64.8 (#30), Qwen3.7 Max: 62.4 (#32)

BenchmarkDeepSeek V4 ProQwen3.7 Max
FrontierMath (Tiers 1-3)64.6%64.6%
FrontierMath Tier 426.8%34.1%
OTIS Mock AIME 2024-202598.6%95.6%
ProofBench50%26%
LMArena Math14551490
MathArena Final-Answer Competitions76.6%—

Knowledge Qwen3.7 Max leads

DeepSeek V4 Pro: 59.5 (#31), Qwen3.7 Max: 61.6 (#28)

BenchmarkDeepSeek V4 ProQwen3.7 Max
GPQA Diamond91.7%90.9%
SimpleQA Verified52.9%55.8%
LMArena Expert14641488
Vectara Hallucination Rate8.6%—

Multilingual Qwen3.7 Max leads

DeepSeek V4 Pro: 54.4 (#45), Qwen3.7 Max: 56.9 (#15)

BenchmarkDeepSeek V4 ProQwen3.7 Max
LMArena Non-English14391474
LMArena Chinese14861530
LMArena Russian14531484
LMArena French1472—
LMArena German1458—
LMArena Japanese1445—
LMArena Korean1447—
LMArena Spanish1458—

Instruction Following Too close to call

DeepSeek V4 Pro: 76.1 (#47), Qwen3.7 Max: 76.7 (#38)

BenchmarkDeepSeek V4 ProQwen3.7 Max
LMArena Instruction Following14481460

Long Context Too close to call

DeepSeek V4 Pro: 45.0 (#51), Qwen3.7 Max: 45.4 (#40)

BenchmarkDeepSeek V4 ProQwen3.7 Max
LMArena Longer Query14581482
CL-bench Life13.5%—

Writing & Preference Too close to call

DeepSeek V4 Pro: 65.5 (#46), Qwen3.7 Max: 65.0 (#54)

BenchmarkDeepSeek V4 ProQwen3.7 Max
LMArena Text14511476
LMArena Creative Writing14461449
EQ-Bench 411661110
LMArena Multi-Turn14671481
EQ-Bench Creative Writing1553—

Frequently asked questions

Is DeepSeek V4 Pro better than Qwen3.7 Max?

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 51.5 on the Noometry Index.

Which is cheaper, DeepSeek V4 Pro or Qwen3.7 Max?

DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

Is DeepSeek V4 Pro or Qwen3.7 Max better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 50.4 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do DeepSeek V4 Pro and Qwen3.7 Max share?

30 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen3.7 Max has 33.

Related comparisons

Go deeper