Noometry

Model comparison

DeepSeek-V3.1 vs Qwen Max

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 34.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.8

Rank #108 Confirmed

Qwen Max Alibaba (Qwen)

34.7

Rank #230 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Qwen Max in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 22.3.
  • The biggest single-benchmark swing is Fiction.LiveBench: 52.8% for DeepSeek-V3.1 and 66.7% for Qwen Max.
  • DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
  • DeepSeek-V3.1 accepts more context: 164K tokens versus 33K.
  • DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1Qwen Max
ProviderDeepSeekAlibaba (Qwen)
Noometry Index42.834.7
Released2025-08-212024-04-03
WeightsOpenProprietary
Context window164K33K
Max output8K8K
Input $ / M tokens$0.25$1.60
Output $ / M tokens$0.95$6.40
Results tracked2723

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 40.3 (#144), Qwen Max: 30.7 (#292)

BenchmarkDeepSeek-V3.1Qwen Max
LMArena Coding14171288
Aider Polyglot—21.8%
WeirdML38.4%—

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.9 (#110), Qwen Max: 25.1 (#151)

BenchmarkDeepSeek-V3.1Qwen Max
LMArena Hard Prompts14171269
SimpleBench40%—
Kagi LLM Benchmark53.2%—
DTBench82.7%—
LMCA24.3%—
Epoch Capabilities Index139.92—
ForecastBench58—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 38.9 (#122), Qwen Max: 22.3 (#276)

BenchmarkDeepSeek-V3.1Qwen Max
LMArena Math14201275
OTIS Mock AIME 2024-2025—16.1%
MATH Level 5—67.2%
FrontierMath (Feb 2025 set)—1%

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.7 (#90), Qwen Max: 30.3 (#228)

BenchmarkDeepSeek-V3.1Qwen Max
LMArena Expert14051248
GPQA Diamond—56.1%
Vectara Hallucination Rate5.5%—

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.6 (#106), Qwen Max: 41.8 (#202)

BenchmarkDeepSeek-V3.1Qwen Max
LMArena Non-English14001263
LMArena Chinese14691254
LMArena French14471330
LMArena German14111254
LMArena Japanese13781205
LMArena Korean13371142
LMArena Russian14051274
LMArena Spanish14311290

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 73.9 (#110), Qwen Max: 66.5 (#208)

BenchmarkDeepSeek-V3.1Qwen Max
LMArena Instruction Following14001262

Long Context Qwen Max leads

DeepSeek-V3.1: 36.3 (#232), Qwen Max: 39.4 (#180)

BenchmarkDeepSeek-V3.1Qwen Max
Fiction.LiveBench52.8%66.7%
LMArena Longer Query14221288

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.3 (#98), Qwen Max: 47.8 (#205)

BenchmarkDeepSeek-V3.1Qwen Max
LMArena Text14201282
LMArena Creative Writing14011248
LMArena Multi-Turn14081277
EQ-Bench Creative Writing1436—

Frequently asked questions

Is DeepSeek-V3.1 better than Qwen Max?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 34.7 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or Qwen Max?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Qwen Max lists at $1.60 and $6.40.

Is DeepSeek-V3.1 or Qwen Max better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 30.7 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 33K.

How many benchmarks do DeepSeek-V3.1 and Qwen Max share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen Max has 23.

Related comparisons

Go deeper