Noometry

Model comparison

GPT-5 Nano vs Qwen2-72B

GPT-5 Nano is the stronger model overall, scoring 33.4 to 29.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-5 Nano OpenAI

33.4

Rank #234 Confirmed

Qwen2-72B Alibaba (Qwen)

29.5

Rank #294 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-5 Nano scores higher in 6 categories and Qwen2-72B in 3 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5 Nano leads 35.8 to 21.2.
  • The biggest single-benchmark swing is MATH Level 5: 95.2% for GPT-5 Nano and 39.1% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

GPT-5 NanoQwen2-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index33.429.5
Released2025-08-072024-06-07
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.05—
Output $ / M tokens$0.40—
Results tracked4826

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

Category by category

Coding GPT-5 Nano leads

GPT-5 Nano: 33.3 (#248), Qwen2-72B: 28.7 (#303)

BenchmarkGPT-5 NanoQwen2-72B
WeirdML38.1%11.3%
LMArena Coding13511196
SWE-bench Verified (bash only)34.8%—
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench718.67—

Agentic & Tool Use GPT-5 Nano leads

GPT-5 Nano: 25.6 (#99), Qwen2-72B: 16.9 (#138)

BenchmarkGPT-5 NanoQwen2-72B
Terminal-Bench21.8%—
Berkeley Function Calling Leaderboard51.5%—
TheAgentCompany—1.1%
METR Time Horizons—29.9%

Reasoning Qwen2-72B leads

GPT-5 Nano: 16.4 (#291), Qwen2-72B: 22.2 (#184)

BenchmarkGPT-5 NanoQwen2-72B
LMArena Hard Prompts13291191
Epoch Capabilities Index139.39125.27
ARC-AGI-22.6%—
Kagi LLM Benchmark62.2%—
ARC-AGI-120.7%—
Chess Puzzles27%—
Mystery Game Puzzles9%—
DTBench62.7%—
LMCA7.9%—
ForecastBench59.1—

Math GPT-5 Nano leads

GPT-5 Nano: 29.1 (#221), Qwen2-72B: 27.9 (#232)

BenchmarkGPT-5 NanoQwen2-72B
LMArena Math13181235
MATH Level 595.2%39.1%
FrontierMath (Tiers 1-3)20%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202581.1%—
ProofBench12%—
Omni-MATH54.6%—
FrontierMath (Feb 2025 set)8.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5 Nano leads

GPT-5 Nano: 35.8 (#166), Qwen2-72B: 21.2 (#270)

BenchmarkGPT-5 NanoQwen2-72B
GPQA Diamond69.4%40.8%
LMArena Expert13211171
SimpleQA Verified11.7%—
MMLU-Pro77.8%—
Vectara Hallucination Rate10.5%—
GPQA (HELM)67.9%—
MMLU—82.4%

Multimodal Not comparable

GPT-5 Nano: 30.7 (#102), Qwen2-72B: —

BenchmarkGPT-5 NanoQwen2-72B
LMArena Vision1159—
VPCT37.2%—

Multilingual GPT-5 Nano leads

GPT-5 Nano: 45.5 (#167), Qwen2-72B: 36.0 (#239)

BenchmarkGPT-5 NanoQwen2-72B
LMArena Non-English13131176
LMArena Chinese13551240
LMArena German13291151
LMArena Korean12691083
LMArena Russian12961169
LMArena Spanish13601168
LMArena French—1169
LMArena Japanese—1111

Instruction Following GPT-5 Nano leads

GPT-5 Nano: 75.2 (#72), Qwen2-72B: 62.0 (#236)

BenchmarkGPT-5 NanoQwen2-72B
LMArena Instruction Following13061181
IFEval93.2%—

Long Context Qwen2-72B leads

GPT-5 Nano: 31.3 (#275), Qwen2-72B: 36.1 (#230)

BenchmarkGPT-5 NanoQwen2-72B
LMArena Longer Query13131193
Fiction.LiveBench44.4%—

Writing & Preference Qwen2-72B leads

GPT-5 Nano: 39.4 (#244), Qwen2-72B: 41.0 (#236)

BenchmarkGPT-5 NanoQwen2-72B
LMArena Text13201203
LMArena Creative Writing12501181
LMArena Multi-Turn13111195
EQ-Bench Creative Writing705—
WildBench80.6%—

Frequently asked questions

Is GPT-5 Nano better than Qwen2-72B?

GPT-5 Nano is the stronger model overall, scoring 33.4 to 29.5 on the Noometry Index.

Is GPT-5 Nano or Qwen2-72B better for coding?

GPT-5 Nano scores higher on coding benchmarks: 33.3 versus 28.7 in the Noometry coding category.

How many benchmarks do GPT-5 Nano and Qwen2-72B share?

19 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper