Noometry

Model comparison

GPT-4o mini vs Qwen1.5-72B

Qwen1.5-72B is the stronger model overall, scoring 30.8 to 25.5 on the Noometry Index.

Last verified . 22 shared benchmarks.

GPT-4o mini OpenAI

25.5

Rank #343 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-4o 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 math, where Qwen1.5-72B leads 33.2 to 10.4.
  • The biggest single-benchmark swing is BigCodeBench Complete: 57.4% for GPT-4o mini and 40.3% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

GPT-4o miniQwen1.5-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index25.530.8
Released2024-07-182024-02-04
WeightsProprietaryOpen
Context window128K—
Max output16K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked6022

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

Category by category

Coding Qwen1.5-72B leads

GPT-4o mini: 22.0 (#335), Qwen1.5-72B: 31.9 (#277)

BenchmarkGPT-4o miniQwen1.5-72B
BigCodeBench Instruct46.1%33.2%
LMArena Coding12901165
BigCodeBench Complete57.4%40.3%
HumanEval+83.5%59.1%
MBPP+72.2%61.6%
Aider Polyglot3.6%—
WeirdML11.8%—
LiveBench Coding43.1%—

Agentic & Tool Use Not comparable

GPT-4o mini: 27.5 (#101), Qwen1.5-72B: —

BenchmarkGPT-4o miniQwen1.5-72B
BALROG17.4%—

Reasoning Qwen1.5-72B leads

GPT-4o mini: 8.7 (#347), Qwen1.5-72B: 22.2 (#203)

BenchmarkGPT-4o miniQwen1.5-72B
LMArena Hard Prompts12671148
ARC-AGI-20%—
SimpleBench10.7%—
Kagi LLM Benchmark28.8%—
Chess Puzzles0%—
LiveBench Reasoning32.8%—
Mystery Game Puzzles12%—
DTBench54.4%—
LiveBench Data Analysis50%—
LMCA10.4%—
Epoch Capabilities Index126.56—
LiveBench41.3%—
PIQA88.7%—

Math Qwen1.5-72B leads

GPT-4o mini: 10.4 (#314), Qwen1.5-72B: 33.2 (#205)

BenchmarkGPT-4o miniQwen1.5-72B
LMArena Math12671164
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.9%—
Omni-MATH28%—
LiveBench Math36.3%—
MATH Level 552.6%—
GSM8K91.3%—

Knowledge GPT-4o mini leads

GPT-4o mini: 17.7 (#284), Qwen1.5-72B: 11.5 (#300)

BenchmarkGPT-4o miniQwen1.5-72B
GPQA Diamond37.7%28.8%
LMArena Expert12351136
SimpleQA Verified8.3%—
MMLU-Pro60.3%—
Confabulations37.2%—
GPQA (HELM)36.8%—
BoolQ88.7%—
MMLU81.8%—

Multimodal Not comparable

GPT-4o mini: 25.9 (#122), Qwen1.5-72B: —

BenchmarkGPT-4o miniQwen1.5-72B
LMArena Vision1066—
Video-MME64.8%—
GeoBench64%—
VPCT34%—

Multilingual GPT-4o mini leads

GPT-4o mini: 42.0 (#199), Qwen1.5-72B: 33.2 (#253)

BenchmarkGPT-4o miniQwen1.5-72B
LMArena Non-English12661135
LMArena Chinese12651186
LMArena French12971159
LMArena German12721084
LMArena Japanese12161061
LMArena Korean11951050
LMArena Russian12751104
LMArena Spanish12761110

Instruction Following GPT-4o mini leads

GPT-4o mini: 61.9 (#239), Qwen1.5-72B: 59.3 (#256)

BenchmarkGPT-4o miniQwen1.5-72B
LMArena Instruction Following12581141
LiveBench Instruction Following56.8%—
IFEval78.2%—

Long Context GPT-4o mini leads

GPT-4o mini: 39.1 (#186), Qwen1.5-72B: 35.1 (#243)

BenchmarkGPT-4o miniQwen1.5-72B
LMArena Longer Query12891157

Writing & Preference GPT-4o mini leads

GPT-4o mini: 39.5 (#248), Qwen1.5-72B: 37.3 (#258)

BenchmarkGPT-4o miniQwen1.5-72B
LMArena Text12861166
LMArena Creative Writing12681137
LMArena Multi-Turn12851160
Short-Story Creative Writing67.2%—
EQ-Bench Creative Writing873—
WildBench79.1%—
LiveBench Language28.6%—

Frequently asked questions

Is GPT-4o mini better than Qwen1.5-72B?

Qwen1.5-72B is the stronger model overall, scoring 30.8 to 25.5 on the Noometry Index.

Is GPT-4o mini or Qwen1.5-72B better for coding?

Qwen1.5-72B scores higher on coding benchmarks: 31.9 versus 22.0 in the Noometry coding category.

How many benchmarks do GPT-4o mini and Qwen1.5-72B share?

22 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper