Noometry

Model comparison

GPT-4.1 mini vs Qwen1.5-72B

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 30.8 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4.1 mini scores higher in 4 categories and Qwen1.5-72B in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.1 mini leads 34.7 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 65.8% for GPT-4.1 mini and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniQwen1.5-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index33.630.8
Released2025-04-142024-02-04
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4722

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

Category by category

Coding Qwen1.5-72B leads

GPT-4.1 mini: 30.6 (#293), Qwen1.5-72B: 31.9 (#277)

BenchmarkGPT-4.1 miniQwen1.5-72B
BigCodeBench Instruct48.9%33.2%
LMArena Coding13671165
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Complete—40.3%
CadEval16%—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.3 (#55), Qwen1.5-72B: —

BenchmarkGPT-4.1 miniQwen1.5-72B
Berkeley Function Calling Leaderboard50.5%—

Reasoning Qwen1.5-72B leads

GPT-4.1 mini: 10.8 (#340), Qwen1.5-72B: 22.2 (#203)

BenchmarkGPT-4.1 miniQwen1.5-72B
LMArena Hard Prompts13491148
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—
Epoch Capabilities Index135.01—

Math Qwen1.5-72B leads

GPT-4.1 mini: 24.1 (#270), Qwen1.5-72B: 33.2 (#205)

BenchmarkGPT-4.1 miniQwen1.5-72B
LMArena Math13431164
FrontierMath (Tiers 1-3)6.7%—
OTIS Mock AIME 2024-202544.7%—
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge GPT-4.1 mini leads

GPT-4.1 mini: 34.7 (#194), Qwen1.5-72B: 11.5 (#300)

BenchmarkGPT-4.1 miniQwen1.5-72B
GPQA Diamond65.8%28.8%
LMArena Expert13381136
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), Qwen1.5-72B: —

BenchmarkGPT-4.1 miniQwen1.5-72B
LMArena Vision1181—

Multilingual GPT-4.1 mini leads

GPT-4.1 mini: 45.7 (#166), Qwen1.5-72B: 33.2 (#253)

BenchmarkGPT-4.1 miniQwen1.5-72B
LMArena Non-English13181135
LMArena Chinese13291186
LMArena French13581159
LMArena German13511084
LMArena Japanese12901061
LMArena Korean12981050
LMArena Russian13241104
LMArena Spanish13191110

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.7 (#118), Qwen1.5-72B: 59.3 (#256)

BenchmarkGPT-4.1 miniQwen1.5-72B
LMArena Instruction Following13331141
IFEval90.4%—

Long Context Qwen1.5-72B leads

GPT-4.1 mini: 31.8 (#275), Qwen1.5-72B: 35.1 (#243)

BenchmarkGPT-4.1 miniQwen1.5-72B
LMArena Longer Query13441157
Fiction.LiveBench44.4%—

Writing & Preference GPT-4.1 mini leads

GPT-4.1 mini: 48.6 (#199), Qwen1.5-72B: 37.3 (#258)

BenchmarkGPT-4.1 miniQwen1.5-72B
LMArena Text13401166
LMArena Creative Writing13001137
LMArena Multi-Turn13541160
EQ-Bench Creative Writing1147—
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than Qwen1.5-72B?

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 30.8 on the Noometry Index.

Is GPT-4.1 mini or Qwen1.5-72B better for coding?

Qwen1.5-72B scores higher on coding benchmarks: 31.9 versus 30.6 in the Noometry coding category.

How many benchmarks do GPT-4.1 mini and Qwen1.5-72B share?

19 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper