Noometry

Model comparison

DeepSeek-V3.1-Terminus vs QwQ-32B

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 39.4 on the Noometry Index.

Last verified . 10 shared benchmarks.

DeepSeek-V3.1-Terminus DeepSeek

42.6

Rank #96 Confirmed

QwQ-32B Alibaba (Qwen)

39.4

Rank #153 Confirmed

Summary

  • They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 5 categories and QwQ-32B in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 50.9.

Side by side

DeepSeek-V3.1-TerminusQwQ-32B
ProviderDeepSeekAlibaba (Qwen)
Noometry Index42.639.4
Released2025-09-222024-11-28
WeightsOpenOpen
Context window164K—
Max output66K—
Input $ / M tokens$0.30—
Output $ / M tokens$1—
Results tracked1636

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

Category by category

Coding DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 41.5 (#114), QwQ-32B: 34.9 (#220)

BenchmarkDeepSeek-V3.1-TerminusQwQ-32B
LMArena Coding14261333
Aider Polyglot—20.9%
SciCode40.6%—
BigCodeBench Instruct—44.6%
LiveBench Coding—72.2%
BigCodeBench Complete—54.4%
ALE-Bench745.17—

Reasoning DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 25.7 (#126), QwQ-32B: 22.9 (#171)

BenchmarkDeepSeek-V3.1-TerminusQwQ-32B
LMArena Hard Prompts14271326
Kagi LLM Benchmark57.4%—
CritPt1.7%—
Chess Puzzles—5%
LiveBench Reasoning—83.5%
DTBench81.3%—
LiveBench Data Analysis—65%
LMCA28.6%—
Epoch Capabilities Index—137.6
ForecastBench—58.3
LiveBench—72%

Math Too close to call

DeepSeek-V3.1-Terminus: 35.7 (#138), QwQ-32B: 36.2 (#123)

BenchmarkDeepSeek-V3.1-TerminusQwQ-32B
LMArena Math14021359
OTIS Mock AIME 2024-2025—59.2%
LiveBench Math—77.8%

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, QwQ-32B: 37.2 (#150)

BenchmarkDeepSeek-V3.1-TerminusQwQ-32B
GPQA Diamond—65.3%
Confabulations—15.6%
LMArena Expert—1323

Multilingual DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 52.3 (#87), QwQ-32B: 45.0 (#171)

BenchmarkDeepSeek-V3.1-TerminusQwQ-32B
LMArena Non-English14071306
LMArena Russian14341297
LMArena Chinese—1378
LMArena French—1337
LMArena German—1313
LMArena Japanese—1263
LMArena Korean—1278
LMArena Spanish—1353

Instruction Following DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 74.4 (#96), QwQ-32B: 72.8 (#131)

BenchmarkDeepSeek-V3.1-TerminusQwQ-32B
LMArena Instruction Following14061297
LiveBench Instruction Following—81.8%

Long Context QwQ-32B leads

DeepSeek-V3.1-Terminus: 43.5 (#88), QwQ-32B: 49.0 (#11)

BenchmarkDeepSeek-V3.1-TerminusQwQ-32B
LMArena Longer Query14261308
Fiction.LiveBench—83.3%

Writing & Preference DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 61.3 (#87), QwQ-32B: 50.9 (#175)

BenchmarkDeepSeek-V3.1-TerminusQwQ-32B
LMArena Text14201329
LMArena Creative Writing14041288
LMArena Multi-Turn14111314
Short-Story Creative Writing—80.2%
EQ-Bench Creative Writing—1257
LiveBench Language—51.4%

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than QwQ-32B?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 39.4 on the Noometry Index.

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

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 34.9 in the Noometry coding category.

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

10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper