Noometry

Model comparison

GPT-4 Turbo vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.8 to 30.5 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4 Turbo 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 9.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 59.2% for QwQ-32B.
  • QwQ-32B has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboQwQ-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index30.539.8
Released2023-11-062024-11-28
WeightsProprietaryOpen
Context window128K—
Max output4K—
Input $ / M tokens$10—
Output $ / M tokens$30—
Results tracked3636

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

Category by category

Coding QwQ-32B leads

GPT-4 Turbo: 33.8 (#249), QwQ-32B: 35.4 (#226)

BenchmarkGPT-4 TurboQwQ-32B
BigCodeBench Instruct48.2%44.6%
LMArena Coding12681333
BigCodeBench Complete58.2%54.4%
Aider Polyglot—20.9%
WeirdML18%—
LiveBench Coding—72.2%
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, QwQ-32B: —

BenchmarkGPT-4 TurboQwQ-32B
METR Time Horizons36.7%—

Reasoning QwQ-32B leads

GPT-4 Turbo: 15.3 (#317), QwQ-32B: 23.7 (#174)

BenchmarkGPT-4 TurboQwQ-32B
Chess Puzzles6%5%
LMArena Hard Prompts12511325
Epoch Capabilities Index127.25137.6
ForecastBench59.458.3
SimpleBench25.1%—
LiveBench Reasoning—83.5%
DTBench61.6%—
LiveBench Data Analysis—65%
LMCA9.8%—
LiveBench—72%

Math QwQ-32B leads

GPT-4 Turbo: 9.0 (#322), QwQ-32B: 38.0 (#143)

BenchmarkGPT-4 TurboQwQ-32B
OTIS Mock AIME 2024-20256.7%59.2%
LMArena Math12721359
FrontierMath (Tiers 1-3)0.7%—
LiveBench Math—77.8%
MATH Level 546.7%—

Knowledge QwQ-32B leads

GPT-4 Turbo: 24.3 (#268), QwQ-32B: 37.2 (#158)

BenchmarkGPT-4 TurboQwQ-32B
GPQA Diamond46.6%65.3%
Confabulations28.4%15.6%
LMArena Expert12231324
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), QwQ-32B: —

BenchmarkGPT-4 TurboQwQ-32B
LMArena Vision1090—

Multilingual QwQ-32B leads

GPT-4 Turbo: 40.5 (#216), QwQ-32B: 44.8 (#176)

BenchmarkGPT-4 TurboQwQ-32B
LMArena Non-English12451305
LMArena Chinese12421378
LMArena French12761336
LMArena German12591313
LMArena Japanese11941262
LMArena Korean11871279
LMArena Russian12591297
LMArena Spanish12601354

Instruction Following QwQ-32B leads

GPT-4 Turbo: 65.8 (#216), QwQ-32B: 72.6 (#137)

BenchmarkGPT-4 TurboQwQ-32B
LMArena Instruction Following12491297
LiveBench Instruction Following—81.8%

Long Context QwQ-32B leads

GPT-4 Turbo: 38.0 (#206), QwQ-32B: 49.0 (#11)

BenchmarkGPT-4 TurboQwQ-32B
LMArena Longer Query12541308
Fiction.LiveBench—83.3%

Writing & Preference QwQ-32B leads

GPT-4 Turbo: 47.7 (#206), QwQ-32B: 50.6 (#180)

BenchmarkGPT-4 TurboQwQ-32B
LMArena Text12721329
LMArena Creative Writing12691288
LMArena Multi-Turn12671314
Short-Story Creative Writing—80.2%
EQ-Bench Creative Writing—1257
LiveBench Language—51.4%

Frequently asked questions

Is GPT-4 Turbo better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 30.5 on the Noometry Index.

Is GPT-4 Turbo or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 35.4 versus 33.8 in the Noometry coding category.

How many benchmarks do GPT-4 Turbo and QwQ-32B share?

25 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper