Noometry

Model comparison

o1 vs Qwen2-72B

o1 is the stronger model overall, scoring 40.9 to 30.0 on the Noometry Index.

Last verified . 22 shared benchmarks.

o1 OpenAI

40.9

Rank #143 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 22 benchmarks with published results for both. o1 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where o1 leads 41.5 to 21.2.
  • The biggest single-benchmark swing is MATH Level 5: 94.7% for o1 and 39.1% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

o1Qwen2-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index40.930.0
Released2024-09-122024-06-07
WeightsProprietaryOpen
Context window200K—
Max output100K—
Input $ / M tokens$15—
Output $ / M tokens$60—
Results tracked5226

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

Category by category

Coding o1 leads

o1: 46.1 (#70), Qwen2-72B: 29.1 (#310)

Benchmarko1Qwen2-72B
WeirdML47.6%11.3%
LMArena Coding13671196
Aider Polyglot61.7%—
BigCodeBench Instruct—38.5%
LiveBench Coding69.7%—
BigCodeBench Complete—54%
CadEval56%—
HumanEval+89%—
MBPP+80.2%—

Agentic & Tool Use o1 leads

o1: 24.6 (#117), Qwen2-72B: 17.0 (#146)

Benchmarko1Qwen2-72B
METR Time Horizons51.1%29.9%
TheAgentCompany—1.1%
Cybench10%—

Reasoning o1 leads

o1: 27.9 (#111), Qwen2-72B: 23.2 (#181)

Benchmarko1Qwen2-72B
LMArena Hard Prompts13711191
Epoch Capabilities Index141.91125.28
SimpleBench41.7%—
ARC-AGI-130.7%—
Chess Puzzles15%—
EnigmaEval5.7%—
LiveBench Reasoning91.6%—
DTBench74.7%—
LiveBench Data Analysis65.5%—
LMCA22.3%—
LiveBench75.7%—

Math o1 leads

o1: 36.1 (#175), Qwen2-72B: 30.2 (#236)

Benchmarko1Qwen2-72B
LMArena Math13881235
MATH Level 594.7%39.1%
FrontierMath (Tiers 1-3)14.7%—
OTIS Mock AIME 2024-202573.3%—
LiveBench Math80.3%—
FrontierMath (Feb 2025 set)9.3%—

Knowledge o1 leads

o1: 41.5 (#110), Qwen2-72B: 21.2 (#275)

Benchmarko1Qwen2-72B
GPQA Diamond76.8%40.8%
LMArena Expert13611171
Humanity's Last Exam8%—
SimpleQA Verified41.1%—
Confabulations11.7%—
MMLU—82.4%

Multimodal Not comparable

o1: 34.2 (#93), Qwen2-72B: —

Benchmarko1Qwen2-72B
LMArena Vision1168—
GeoBench80%—
VPCT37%—
SpatialViz-Bench41.4%—

Multilingual o1 leads

o1: 48.6 (#142), Qwen2-72B: 35.9 (#244)

Benchmarko1Qwen2-72B
LMArena Non-English13581176
LMArena Chinese13941240
LMArena French13441170
LMArena German13371151
LMArena Japanese13461111
LMArena Korean13961083
LMArena Russian13561169
LMArena Spanish13451169

Instruction Following o1 leads

o1: 74.8 (#86), Qwen2-72B: 61.7 (#241)

Benchmarko1Qwen2-72B
LMArena Instruction Following13671181
LiveBench Instruction Following81.5%—

Long Context o1 leads

o1: 50.3 (#9), Qwen2-72B: 36.1 (#235)

Benchmarko1Qwen2-72B
LMArena Longer Query13781192
Fiction.LiveBench83.3%—

Writing & Preference o1 leads

o1: 55.6 (#144), Qwen2-72B: 40.8 (#241)

Benchmarko1Qwen2-72B
LMArena Text13661203
LMArena Creative Writing13481181
LMArena Multi-Turn13691196
Short-Story Creative Writing70.2%—
LiveBench Language65.4%—

Frequently asked questions

Is o1 better than Qwen2-72B?

o1 is the stronger model overall, scoring 40.9 to 30.0 on the Noometry Index.

Is o1 or Qwen2-72B better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 29.1 in the Noometry coding category.

How many benchmarks do o1 and Qwen2-72B share?

22 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper