Noometry

Model comparison

GPT-4.1 vs Qwen2-72B

GPT-4.1 is the stronger model overall, scoring 35.7 to 29.5 on the Noometry Index.

Last verified . 21 shared benchmarks.

GPT-4.1 OpenAI

35.7

Rank #215 Confirmed

Qwen2-72B Alibaba (Qwen)

29.5

Rank #294 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-4.1 scores higher in 7 categories and Qwen2-72B in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where GPT-4.1 leads 34.4 to 16.9.
  • The biggest single-benchmark swing is MATH Level 5: 83% for GPT-4.1 and 39.1% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1Qwen2-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index35.729.5
Released2025-04-142024-06-07
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$2—
Output $ / M tokens$8—
Results tracked5226

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

Category by category

Coding GPT-4.1 leads

GPT-4.1: 34.2 (#228), Qwen2-72B: 28.7 (#303)

BenchmarkGPT-4.1Qwen2-72B
WeirdML39%11.3%
LMArena Coding13911196
SWE-bench Verified48.5%—
SWE-bench Verified (bash only)39.6%—
Aider Polyglot52.4%—
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
CadEval42%—
ALE-Bench558.1—

Agentic & Tool Use GPT-4.1 leads

GPT-4.1: 34.4 (#40), Qwen2-72B: 16.9 (#138)

BenchmarkGPT-4.1Qwen2-72B
Berkeley Function Calling Leaderboard54%—
TheAgentCompany—1.1%
METR Time Horizons—29.9%

Reasoning Qwen2-72B leads

GPT-4.1: 11.7 (#334), Qwen2-72B: 22.2 (#184)

BenchmarkGPT-4.1Qwen2-72B
LMArena Hard Prompts13841191
Epoch Capabilities Index136.79125.27
ARC-AGI-20.4%—
SimpleBench27%—
Kagi LLM Benchmark52.3%—
ARC-AGI-15.5%—
Chess Puzzles6%—
EnigmaEval2.2%—
DTBench68.3%—
LMCA25.6%—
ForecastBench61.5—

Math Qwen2-72B leads

GPT-4.1: 21.4 (#269), Qwen2-72B: 27.9 (#232)

BenchmarkGPT-4.1Qwen2-72B
LMArena Math13691235
MATH Level 583%39.1%
FrontierMath (Tiers 1-3)6%—
OTIS Mock AIME 2024-202538.3%—
Omni-MATH47.1%—
FrontierMath (Feb 2025 set)5.5%—
FrontierMath Tier 4 (v1)0%—

Knowledge GPT-4.1 leads

GPT-4.1: 37.0 (#152), Qwen2-72B: 21.2 (#270)

BenchmarkGPT-4.1Qwen2-72B
GPQA Diamond66.9%40.8%
LMArena Expert13641171
Humanity's Last Exam5.4%—
SimpleQA Verified31.1%—
MMLU-Pro81.1%—
Vectara Hallucination Rate5.6%—
GPQA (HELM)65.9%—
MMLU—82.4%

Multimodal Not comparable

GPT-4.1: 37.5 (#66), Qwen2-72B: —

BenchmarkGPT-4.1Qwen2-72B
LMArena Vision1210—
GeoBench72%—

Multilingual GPT-4.1 leads

GPT-4.1: 49.6 (#128), Qwen2-72B: 36.0 (#239)

BenchmarkGPT-4.1Qwen2-72B
LMArena Non-English13701176
LMArena Chinese13821240
LMArena French13831169
LMArena German13801151
LMArena Japanese13201111
LMArena Korean13391083
LMArena Russian13771169
LMArena Spanish13751168

Instruction Following GPT-4.1 leads

GPT-4.1: 71.5 (#148), Qwen2-72B: 62.0 (#236)

BenchmarkGPT-4.1Qwen2-72B
LMArena Instruction Following13671181
IFEval83.8%—

Long Context GPT-4.1 leads

GPT-4.1: 40.0 (#158), Qwen2-72B: 36.1 (#230)

BenchmarkGPT-4.1Qwen2-72B
LMArena Longer Query13851193
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.1 leads

GPT-4.1: 57.8 (#120), Qwen2-72B: 41.0 (#236)

BenchmarkGPT-4.1Qwen2-72B
LMArena Text13831203
LMArena Creative Writing13631181
LMArena Multi-Turn13981195
EQ-Bench Creative Writing1420—
WildBench85.4%—

Frequently asked questions

Is GPT-4.1 better than Qwen2-72B?

GPT-4.1 is the stronger model overall, scoring 35.7 to 29.5 on the Noometry Index.

Is GPT-4.1 or Qwen2-72B better for coding?

GPT-4.1 scores higher on coding benchmarks: 34.2 versus 28.7 in the Noometry coding category.

How many benchmarks do GPT-4.1 and Qwen2-72B share?

21 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper