Noometry

Model comparison

GPT-5.4 nano vs Qwen1.5-72B

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 30.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-5.4 nano OpenAI

41.9

Rank #125 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-5.4 nano scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 nano leads 41.9 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 78.5% for GPT-5.4 nano and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 nanoQwen1.5-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index41.930.8
Released2026-03-172024-02-04
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.20—
Output $ / M tokens$1.25—
Results tracked4022

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

Category by category

Coding GPT-5.4 nano leads

GPT-5.4 nano: 43.6 (#84), Qwen1.5-72B: 31.9 (#277)

BenchmarkGPT-5.4 nanoQwen1.5-72B
LMArena Coding14051165
SciCode46.9%—
WeirdML49.2%—
BigCodeBench Instruct—33.2%
BigCodeBench Complete—40.3%
ALE-Bench1,005—
HumanEval+—59.1%
MBPP+—61.6%

Reasoning GPT-5.4 nano leads

GPT-5.4 nano: 23.7 (#173), Qwen1.5-72B: 22.2 (#203)

BenchmarkGPT-5.4 nanoQwen1.5-72B
LMArena Hard Prompts13811148
ARC-AGI-25.7%—
Kagi LLM Benchmark39.7%—
ARC-AGI-151.5%—
CritPt9.3%—
Chess Puzzles30%—
Mystery Game Puzzles9%—
DTBench80.3%—
LMCA36.9%—
Epoch Capabilities Index145.81—
ForecastBench57.3—

Math GPT-5.4 nano leads

GPT-5.4 nano: 40.9 (#88), Qwen1.5-72B: 33.2 (#205)

BenchmarkGPT-5.4 nanoQwen1.5-72B
LMArena Math14061164
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 412.2%—
OTIS Mock AIME 2024-202587.8%—
ProofBench5%—
FrontierMath (Feb 2025 set)25.9%—
FrontierMath Tier 4 (v1)6.3%—

Knowledge GPT-5.4 nano leads

GPT-5.4 nano: 41.9 (#103), Qwen1.5-72B: 11.5 (#300)

BenchmarkGPT-5.4 nanoQwen1.5-72B
GPQA Diamond78.5%28.8%
LMArena Expert13961136
SimpleQA Verified11.7%—
Vectara Hallucination Rate3.1%—

Multimodal Not comparable

GPT-5.4 nano: 36.7 (#78), Qwen1.5-72B: —

BenchmarkGPT-5.4 nanoQwen1.5-72B
LMArena Vision1196—

Multilingual GPT-5.4 nano leads

GPT-5.4 nano: 48.6 (#140), Qwen1.5-72B: 33.2 (#253)

BenchmarkGPT-5.4 nanoQwen1.5-72B
LMArena Non-English13591135
LMArena Chinese13921186
LMArena French13961159
LMArena German13671084
LMArena Japanese13431061
LMArena Korean13201050
LMArena Russian13631104
LMArena Spanish13711110

Instruction Following GPT-5.4 nano leads

GPT-5.4 nano: 71.9 (#144), Qwen1.5-72B: 59.3 (#256)

BenchmarkGPT-5.4 nanoQwen1.5-72B
LMArena Instruction Following13621141

Long Context GPT-5.4 nano leads

GPT-5.4 nano: 41.6 (#137), Qwen1.5-72B: 35.1 (#243)

BenchmarkGPT-5.4 nanoQwen1.5-72B
LMArena Longer Query13661157

Writing & Preference GPT-5.4 nano leads

GPT-5.4 nano: 55.7 (#142), Qwen1.5-72B: 37.3 (#258)

BenchmarkGPT-5.4 nanoQwen1.5-72B
LMArena Text13721166
LMArena Creative Writing13141137
LMArena Multi-Turn13821160

Frequently asked questions

Is GPT-5.4 nano better than Qwen1.5-72B?

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 30.8 on the Noometry Index.

Is GPT-5.4 nano or Qwen1.5-72B better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 31.9 in the Noometry coding category.

How many benchmarks do GPT-5.4 nano and Qwen1.5-72B share?

18 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper