Noometry

Model comparison

o3-mini vs Qwen1.5-72B

o3-mini is the stronger model overall, scoring 36.7 to 30.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

o3-mini OpenAI

36.7

Rank #212 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 18 benchmarks with published results for both. o3-mini scores higher in 5 categories and Qwen1.5-72B in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where o3-mini leads 38.3 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 77% for o3-mini and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

o3-miniQwen1.5-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index36.730.8
Released2024-12-202024-02-04
WeightsProprietaryOpen
Context window200K—
Max output100K—
Input $ / M tokens$1.10—
Output $ / M tokens$4.40—
Results tracked5122

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

Category by category

Coding o3-mini leads

o3-mini: 40.8 (#132), Qwen1.5-72B: 31.9 (#277)

Benchmarko3-miniQwen1.5-72B
LMArena Coding13781165
Aider Polyglot60.4%—
SciCode39.8%—
GSO1.3%—
WeirdML43.7%—
BigCodeBench Instruct—33.2%
LiveBench Coding82.7%—
BigCodeBench Complete—40.3%
CadEval54%—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

o3-mini: 29.6 (#84), Qwen1.5-72B: —

Benchmarko3-miniQwen1.5-72B
Cybench22.5%—

Reasoning Qwen1.5-72B leads

o3-mini: 16.3 (#305), Qwen1.5-72B: 22.2 (#203)

Benchmarko3-miniQwen1.5-72B
LMArena Hard Prompts13661148
ARC-AGI-23%—
SimpleBench22.8%—
ARC-AGI-134.5%—
CritPt0.3%—
Chess Puzzles17%—
LiveBench Reasoning89.6%—
Mystery Game Puzzles7%—
DTBench68.8%—
LiveBench Data Analysis70.6%—
LMCA19%—
Epoch Capabilities Index140.34—
ForecastBench59.6—
LiveBench75.9%—

Math Qwen1.5-72B leads

o3-mini: 28.1 (#244), Qwen1.5-72B: 33.2 (#205)

Benchmarko3-miniQwen1.5-72B
LMArena Math13961164
FrontierMath (Tiers 1-3)18.6%—
FrontierMath Tier 40%—
OTIS Mock AIME 2024-202576.9%—
LiveBench Math77.3%—
MATH Level 596.5%—
FrontierMath (Feb 2025 set)12.4%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge o3-mini leads

o3-mini: 38.3 (#146), Qwen1.5-72B: 11.5 (#300)

Benchmarko3-miniQwen1.5-72B
GPQA Diamond77%28.8%
LMArena Expert13641136
SimpleQA Verified15.3%—
Confabulations17.9%—

Multilingual o3-mini leads

o3-mini: 45.7 (#164), Qwen1.5-72B: 33.2 (#253)

Benchmarko3-miniQwen1.5-72B
LMArena Non-English13191135
LMArena Chinese13791186
LMArena French13341159
LMArena German13031084
LMArena Japanese12861061
LMArena Korean13141050
LMArena Russian13041104
LMArena Spanish13211110

Instruction Following o3-mini leads

o3-mini: 75.1 (#72), Qwen1.5-72B: 59.3 (#256)

Benchmarko3-miniQwen1.5-72B
LMArena Instruction Following13371141
LiveBench Instruction Following84.4%—

Long Context Qwen1.5-72B leads

o3-mini: 33.8 (#256), Qwen1.5-72B: 35.1 (#243)

Benchmarko3-miniQwen1.5-72B
LMArena Longer Query13431157
Fiction.LiveBench50%—

Writing & Preference o3-mini leads

o3-mini: 50.3 (#182), Qwen1.5-72B: 37.3 (#258)

Benchmarko3-miniQwen1.5-72B
LMArena Text13371166
LMArena Creative Writing12861137
LMArena Multi-Turn13201160
Short-Story Creative Writing61.7%—
LiveBench Language50.7%—

Frequently asked questions

Is o3-mini better than Qwen1.5-72B?

o3-mini is the stronger model overall, scoring 36.7 to 30.8 on the Noometry Index.

Is o3-mini or Qwen1.5-72B better for coding?

o3-mini scores higher on coding benchmarks: 40.8 versus 31.9 in the Noometry coding category.

How many benchmarks do o3-mini and Qwen1.5-72B share?

18 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper