Noometry

Model comparison

GPT-6 Astra vs Qwen1.5-72B

GPT-6 Astra is the stronger model overall, scoring 70.8 to 30.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-6 Astra OpenAI

70.8

Rank #1 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-6 Astra 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-6 Astra leads 75.3 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 95.8% for GPT-6 Astra and 28.8% for Qwen1.5-72B.
  • Qwen1.5-72B has downloadable open weights; the other is API-only.

Side by side

GPT-6 AstraQwen1.5-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index70.830.8
Released2026-09-032024-02-04
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked5622

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

Category by category

Coding GPT-6 Astra leads

GPT-6 Astra: 73.7 (#2), Qwen1.5-72B: 31.9 (#277)

BenchmarkGPT-6 AstraQwen1.5-72B
LMArena Coding14871165
DeepSWE74.1%—
FrontierCode53.3%—
LMArena WebDev1786—
FrontierSWE65.5%—
SciCode56.5%—
GSO79.4%—
WeirdML93.6%—
BigCodeBench Instruct—33.2%
MirrorCode46.7%—
BigCodeBench Complete—40.3%
ALE-Bench2,951—
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

GPT-6 Astra: 52.9 (#3), Qwen1.5-72B: —

BenchmarkGPT-6 AstraQwen1.5-72B
APEX-Agents64.7%—
Remote Labor Index20.8%—
BALROG68.3%—
GDP.pdf34.2%—
Vending-Bench 215,515—

Reasoning GPT-6 Astra leads

GPT-6 Astra: 85.1 (#1), Qwen1.5-72B: 22.2 (#203)

BenchmarkGPT-6 AstraQwen1.5-72B
LMArena Hard Prompts14621148
ARC-AGI-295%—
NYT Connections (extended)98.1%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles72%—
EBR-Bench76.2%—
Mystery Game Puzzles84%—
DTBench97.3%—
LMCA64.4%—
Bench to the Future 30.14—
Epoch Capabilities Index166.45—

Math GPT-6 Astra leads

GPT-6 Astra: 93.5 (#2), Qwen1.5-72B: 33.2 (#205)

BenchmarkGPT-6 AstraQwen1.5-72B
LMArena Math14651164
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 497.6%—
OTIS Mock AIME 2024-2025100%—
ProofBench99%—
FrontierMath Erdős2.9%—

Knowledge GPT-6 Astra leads

GPT-6 Astra: 75.3 (#1), Qwen1.5-72B: 11.5 (#300)

BenchmarkGPT-6 AstraQwen1.5-72B
GPQA Diamond95.8%28.8%
LMArena Expert14831136
Humanity's Last Exam54.8%—
SimpleQA Verified75.6%—
Vectara Hallucination Rate8.7%—

Multimodal Not comparable

GPT-6 Astra: 55.0 (#3), Qwen1.5-72B: —

BenchmarkGPT-6 AstraQwen1.5-72B
LMArena Vision1281—
Blueprint-Bench 249.7%—
Furniture Assembly80%—
LMArena Document1468—

Multilingual GPT-6 Astra leads

GPT-6 Astra: 53.7 (#61), Qwen1.5-72B: 33.2 (#253)

BenchmarkGPT-6 AstraQwen1.5-72B
LMArena Non-English14301135
LMArena Chinese14841186
LMArena French14561159
LMArena German14401084
LMArena Japanese13791061
LMArena Korean14261050
LMArena Russian14361104
LMArena Spanish14071110

Instruction Following GPT-6 Astra leads

GPT-6 Astra: 76.3 (#44), Qwen1.5-72B: 59.3 (#256)

BenchmarkGPT-6 AstraQwen1.5-72B
LMArena Instruction Following14501141

Long Context GPT-6 Astra leads

GPT-6 Astra: 44.5 (#62), Qwen1.5-72B: 35.1 (#243)

BenchmarkGPT-6 AstraQwen1.5-72B
LMArena Longer Query14561157

Writing & Preference GPT-6 Astra leads

GPT-6 Astra: 75.3 (#7), Qwen1.5-72B: 37.3 (#258)

BenchmarkGPT-6 AstraQwen1.5-72B
LMArena Text14411166
LMArena Creative Writing14181137
LMArena Multi-Turn14481160
EQ-Bench Creative Writing2173—

Frequently asked questions

Is GPT-6 Astra better than Qwen1.5-72B?

GPT-6 Astra is the stronger model overall, scoring 70.8 to 30.8 on the Noometry Index.

Is GPT-6 Astra or Qwen1.5-72B better for coding?

GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 31.9 in the Noometry coding category.

How many benchmarks do GPT-6 Astra and Qwen1.5-72B share?

18 benchmarks have published results for both models. GPT-6 Astra has 56 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper