Noometry

Model comparison

Llama 3.1-405B vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.8 to 30.7 on the Noometry Index.

Last verified . 23 shared benchmarks.

Llama 3.1-405B Meta

30.7

Rank #288 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where QwQ-32B leads 38.0 to 18.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 9.7% for Llama 3.1-405B and 59.2% for QwQ-32B.

Side by side

Llama 3.1-405BQwQ-32B
ProviderMetaAlibaba (Qwen)
Noometry Index30.739.8
Released2024-07-232024-11-28
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4236

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

Category by category

Coding QwQ-32B leads

Llama 3.1-405B: 33.1 (#262), QwQ-32B: 35.4 (#226)

BenchmarkLlama 3.1-405BQwQ-32B
LMArena Coding12911333
Aider Polyglot—20.9%
WeirdML21.4%—
BigCodeBench Instruct—44.6%
LiveBench Coding—72.2%
BigCodeBench Complete—54.4%

Agentic & Tool Use Not comparable

Llama 3.1-405B: 21.0 (#140), QwQ-32B: —

BenchmarkLlama 3.1-405BQwQ-32B
TheAgentCompany7.4%—
Cybench7.5%—

Reasoning QwQ-32B leads

Llama 3.1-405B: 16.8 (#300), QwQ-32B: 23.7 (#174)

BenchmarkLlama 3.1-405BQwQ-32B
LMArena Hard Prompts12691325
Epoch Capabilities Index128.75137.6
ForecastBench59.958.3
SimpleBench23%—
Kagi LLM Benchmark45%—
Chess Puzzles—5%
LiveBench Reasoning—83.5%
DTBench61.4%—
LiveBench Data Analysis—65%
BIG-Bench Hard82.9%—
HellaSwag89.2%—
LiveBench—72%
PIQA85.9%—
WinoGrande89.2%—

Math QwQ-32B leads

Llama 3.1-405B: 18.4 (#290), QwQ-32B: 38.0 (#143)

BenchmarkLlama 3.1-405BQwQ-32B
OTIS Mock AIME 2024-20259.7%59.2%
LMArena Math12811359
Omni-MATH24.9%—
LiveBench Math—77.8%
MATH Level 549.8%—

Knowledge QwQ-32B leads

Llama 3.1-405B: 30.4 (#227), QwQ-32B: 37.2 (#158)

BenchmarkLlama 3.1-405BQwQ-32B
GPQA Diamond50.9%65.3%
Confabulations17.6%15.6%
LMArena Expert12431324
MMLU-Pro72.3%—
GPQA (HELM)52.2%—
ARC (AI2) Challenge95.3%—
MMLU84.5%—
TriviaQA82.7%—

Multilingual QwQ-32B leads

Llama 3.1-405B: 40.7 (#214), QwQ-32B: 44.8 (#176)

BenchmarkLlama 3.1-405BQwQ-32B
LMArena Non-English12481305
LMArena Chinese12421378
LMArena French12791336
LMArena German12521313
LMArena Japanese12081262
LMArena Korean11841279
LMArena Russian12651297
LMArena Spanish12601354

Instruction Following QwQ-32B leads

Llama 3.1-405B: 65.9 (#214), QwQ-32B: 72.6 (#137)

BenchmarkLlama 3.1-405BQwQ-32B
LMArena Instruction Following12591297
LiveBench Instruction Following—81.8%
IFEval81.1%—

Long Context QwQ-32B leads

Llama 3.1-405B: 38.4 (#197), QwQ-32B: 49.0 (#11)

BenchmarkLlama 3.1-405BQwQ-32B
LMArena Longer Query12661308
Fiction.LiveBench—83.3%

Writing & Preference QwQ-32B leads

Llama 3.1-405B: 38.9 (#251), QwQ-32B: 50.6 (#180)

BenchmarkLlama 3.1-405BQwQ-32B
LMArena Text12841329
LMArena Creative Writing12621288
EQ-Bench Creative Writing8701257
LMArena Multi-Turn12971314
Short-Story Creative Writing—80.2%
WildBench78.3%—
LiveBench Language—51.4%

Frequently asked questions

Is Llama 3.1-405B better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 30.7 on the Noometry Index.

Is Llama 3.1-405B or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 35.4 versus 33.1 in the Noometry coding category.

How many benchmarks do Llama 3.1-405B and QwQ-32B share?

23 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper