Noometry

Model comparison

GPT-4 Turbo vs Qwen1.5-32B

GPT-4 Turbo and Qwen1.5-32B score almost the same on the Noometry Index (30.5 vs 30.5), so choose on price, context window or the category you care about most.

Last verified . 21 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-4 Turbo scores higher in 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen1.5-32B leads 33.0 to 9.0.
  • The biggest single-benchmark swing is BigCodeBench Complete: 58.2% for GPT-4 Turbo and 42% for Qwen1.5-32B.
  • Qwen1.5-32B has downloadable open weights; the other is API-only.

Side by side

GPT-4 TurboQwen1.5-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index30.530.5
Released2023-11-062024-02-04
WeightsProprietaryOpen
Context window128K—
Max output4K—
Input $ / M tokens$10—
Output $ / M tokens$30—
Results tracked3621

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

Category by category

Coding GPT-4 Turbo leads

GPT-4 Turbo: 33.8 (#249), Qwen1.5-32B: 31.7 (#282)

BenchmarkGPT-4 TurboQwen1.5-32B
BigCodeBench Instruct48.2%32.3%
LMArena Coding12681155
BigCodeBench Complete58.2%42%
WeirdML18%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Qwen1.5-32B: —

BenchmarkGPT-4 TurboQwen1.5-32B
METR Time Horizons36.7%—

Reasoning Qwen1.5-32B leads

GPT-4 Turbo: 15.3 (#317), Qwen1.5-32B: 21.8 (#212)

BenchmarkGPT-4 TurboQwen1.5-32B
LMArena Hard Prompts12511130
SimpleBench25.1%—
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Qwen1.5-32B leads

GPT-4 Turbo: 9.0 (#322), Qwen1.5-32B: 33.0 (#207)

BenchmarkGPT-4 TurboQwen1.5-32B
LMArena Math12721155
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
MATH Level 546.7%—

Knowledge GPT-4 Turbo leads

GPT-4 Turbo: 24.3 (#268), Qwen1.5-32B: 13.5 (#296)

BenchmarkGPT-4 TurboQwen1.5-32B
GPQA Diamond46.6%30.7%
LMArena Expert12231126
MMLU81.3%74.4%
Confabulations28.4%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), Qwen1.5-32B: —

BenchmarkGPT-4 TurboQwen1.5-32B
LMArena Vision1090—

Multilingual GPT-4 Turbo leads

GPT-4 Turbo: 40.5 (#216), Qwen1.5-32B: 31.4 (#259)

BenchmarkGPT-4 TurboQwen1.5-32B
LMArena Non-English12451106
LMArena Chinese12421177
LMArena French12761101
LMArena German12591058
LMArena Japanese11941027
LMArena Korean11871008
LMArena Russian12591073
LMArena Spanish12601089

Instruction Following GPT-4 Turbo leads

GPT-4 Turbo: 65.8 (#216), Qwen1.5-32B: 57.7 (#265)

BenchmarkGPT-4 TurboQwen1.5-32B
LMArena Instruction Following12491116

Long Context GPT-4 Turbo leads

GPT-4 Turbo: 38.0 (#206), Qwen1.5-32B: 34.7 (#246)

BenchmarkGPT-4 TurboQwen1.5-32B
LMArena Longer Query12541146

Writing & Preference GPT-4 Turbo leads

GPT-4 Turbo: 47.7 (#206), Qwen1.5-32B: 34.2 (#271)

BenchmarkGPT-4 TurboQwen1.5-32B
LMArena Text12721137
LMArena Creative Writing12691083
LMArena Multi-Turn12671140

Frequently asked questions

Is GPT-4 Turbo better than Qwen1.5-32B?

GPT-4 Turbo and Qwen1.5-32B score almost the same on the Noometry Index (30.5 vs 30.5), so choose on price, context window or the category you care about most.

Is GPT-4 Turbo or Qwen1.5-32B better for coding?

GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 31.7 in the Noometry coding category.

How many benchmarks do GPT-4 Turbo and Qwen1.5-32B share?

21 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper