Noometry

Model comparison

DeepSeek-V3.1 vs Qwen3 32B

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 39.2 on the Noometry Index.

Last verified . 19 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.8

Rank #108 Confirmed

Qwen3 32B Alibaba (Qwen)

39.2

Rank #172 Confirmed

Summary

  • They share 19 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 6 categories and Qwen3 32B in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 20.2.
  • The biggest single-benchmark swing is Fiction.LiveBench: 52.8% for DeepSeek-V3.1 and 74.2% for Qwen3 32B.
  • DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
  • DeepSeek-V3.1 accepts more context: 164K tokens versus 131K.

Side by side

DeepSeek-V3.1Qwen3 32B
ProviderDeepSeekAlibaba (Qwen)
Noometry Index42.839.2
Released2025-08-212025-04
WeightsOpenOpen
Context window164K131K
Max output8K16K
Input $ / M tokens$0.25$0.70
Output $ / M tokens$0.95$2.80
Results tracked2726

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), Qwen3 32B: 37.7 (#190)

BenchmarkDeepSeek-V3.1Qwen3 32B
LMArena Coding14171358
Aider Polyglot—40%
SciCode—35.4%
WeirdML38.4%—

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, Qwen3 32B: 32.6 (#62)

BenchmarkDeepSeek-V3.1Qwen3 32B
Berkeley Function Calling Leaderboard—48.7%

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.9 (#110), Qwen3 32B: 20.2 (#241)

BenchmarkDeepSeek-V3.1Qwen3 32B
Kagi LLM Benchmark53.2%54.9%
LMArena Hard Prompts14171334
DTBench82.7%67.5%
LMCA24.3%17.3%
Epoch Capabilities Index139.92138.51
SimpleBench40%—
CritPt—0.3%
Chess Puzzles—5%
ForecastBench58—

Math Too close to call

DeepSeek-V3.1: 38.9 (#122), Qwen3 32B: 39.7 (#99)

BenchmarkDeepSeek-V3.1Qwen3 32B
LMArena Math14201399
OTIS Mock AIME 2024-2025—66.9%

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.7 (#90), Qwen3 32B: 40.0 (#125)

BenchmarkDeepSeek-V3.1Qwen3 32B
Vectara Hallucination Rate5.5%5.9%
LMArena Expert14051362
GPQA Diamond—65.7%

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.6 (#106), Qwen3 32B: 45.6 (#167)

BenchmarkDeepSeek-V3.1Qwen3 32B
LMArena Non-English14001317
LMArena Chinese14691357
LMArena German14111341
LMArena Russian14051311
LMArena French1447—
LMArena Japanese1378—
LMArena Korean1337—
LMArena Spanish1431—

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 73.9 (#110), Qwen3 32B: 68.9 (#179)

BenchmarkDeepSeek-V3.1Qwen3 32B
LMArena Instruction Following14001305

Long Context Qwen3 32B leads

DeepSeek-V3.1: 36.3 (#232), Qwen3 32B: 43.8 (#87)

BenchmarkDeepSeek-V3.1Qwen3 32B
Fiction.LiveBench52.8%74.2%
LMArena Longer Query14221327

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.3 (#98), Qwen3 32B: 52.9 (#163)

BenchmarkDeepSeek-V3.1Qwen3 32B
LMArena Text14201340
LMArena Creative Writing14011297
LMArena Multi-Turn14081331
EQ-Bench Creative Writing1436—

Frequently asked questions

Is DeepSeek-V3.1 better than Qwen3 32B?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 39.2 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or Qwen3 32B?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

Is DeepSeek-V3.1 or Qwen3 32B better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 37.7 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 131K.

How many benchmarks do DeepSeek-V3.1 and Qwen3 32B share?

19 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper