Noometry

Model comparison

o1 vs Qwen1.5-32B

o1 is the stronger model overall, scoring 40.9 to 30.5 on the Noometry Index.

Last verified . 18 shared benchmarks.

o1 OpenAI

40.9

Rank #143 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 18 benchmarks with published results for both. o1 scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where o1 leads 41.5 to 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 76.8% for o1 and 30.7% for Qwen1.5-32B.
  • Qwen1.5-32B has downloadable open weights; the other is API-only.

Side by side

o1Qwen1.5-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index40.930.5
Released2024-09-122024-02-04
WeightsProprietaryOpen
Context window200K—
Max output100K—
Input $ / M tokens$15—
Output $ / M tokens$60—
Results tracked5221

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

Category by category

Coding o1 leads

o1: 46.1 (#70), Qwen1.5-32B: 31.7 (#282)

Benchmarko1Qwen1.5-32B
LMArena Coding13671155
Aider Polyglot61.7%—
WeirdML47.6%—
BigCodeBench Instruct—32.3%
LiveBench Coding69.7%—
BigCodeBench Complete—42%
CadEval56%—
HumanEval+89%—
MBPP+80.2%—

Agentic & Tool Use Not comparable

o1: 24.6 (#117), Qwen1.5-32B: —

Benchmarko1Qwen1.5-32B
Cybench10%—
METR Time Horizons51.1%—

Reasoning o1 leads

o1: 27.9 (#111), Qwen1.5-32B: 21.8 (#212)

Benchmarko1Qwen1.5-32B
LMArena Hard Prompts13711130
SimpleBench41.7%—
ARC-AGI-130.7%—
Chess Puzzles15%—
EnigmaEval5.7%—
LiveBench Reasoning91.6%—
DTBench74.7%—
LiveBench Data Analysis65.5%—
LMCA22.3%—
Epoch Capabilities Index141.91—
LiveBench75.7%—

Math o1 leads

o1: 36.1 (#175), Qwen1.5-32B: 33.0 (#207)

Benchmarko1Qwen1.5-32B
LMArena Math13881155
FrontierMath (Tiers 1-3)14.7%—
OTIS Mock AIME 2024-202573.3%—
LiveBench Math80.3%—
MATH Level 594.7%—
FrontierMath (Feb 2025 set)9.3%—

Knowledge o1 leads

o1: 41.5 (#110), Qwen1.5-32B: 13.5 (#296)

Benchmarko1Qwen1.5-32B
GPQA Diamond76.8%30.7%
LMArena Expert13611126
Humanity's Last Exam8%—
SimpleQA Verified41.1%—
Confabulations11.7%—
MMLU—74.4%

Multimodal Not comparable

o1: 34.2 (#93), Qwen1.5-32B: —

Benchmarko1Qwen1.5-32B
LMArena Vision1168—
GeoBench80%—
VPCT37%—
SpatialViz-Bench41.4%—

Multilingual o1 leads

o1: 48.6 (#142), Qwen1.5-32B: 31.4 (#259)

Benchmarko1Qwen1.5-32B
LMArena Non-English13581106
LMArena Chinese13941177
LMArena French13441101
LMArena German13371058
LMArena Japanese13461027
LMArena Korean13961008
LMArena Russian13561073
LMArena Spanish13451089

Instruction Following o1 leads

o1: 74.8 (#86), Qwen1.5-32B: 57.7 (#265)

Benchmarko1Qwen1.5-32B
LMArena Instruction Following13671116
LiveBench Instruction Following81.5%—

Long Context o1 leads

o1: 50.3 (#9), Qwen1.5-32B: 34.7 (#246)

Benchmarko1Qwen1.5-32B
LMArena Longer Query13781146
Fiction.LiveBench83.3%—

Writing & Preference o1 leads

o1: 55.6 (#144), Qwen1.5-32B: 34.2 (#271)

Benchmarko1Qwen1.5-32B
LMArena Text13661137
LMArena Creative Writing13481083
LMArena Multi-Turn13691140
Short-Story Creative Writing70.2%—
LiveBench Language65.4%—

Frequently asked questions

Is o1 better than Qwen1.5-32B?

o1 is the stronger model overall, scoring 40.9 to 30.5 on the Noometry Index.

Is o1 or Qwen1.5-32B better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 31.7 in the Noometry coding category.

How many benchmarks do o1 and Qwen1.5-32B share?

18 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper