Noometry

Model comparison

GPT-6 Astra vs Qwen3.5 Max Preview

GPT-6 Astra is the stronger model overall, scoring 70.8 to 45.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-6 Astra OpenAI

70.8

Rank #1 Confirmed

Qwen3.5 Max Preview Alibaba (Qwen)

45.3

Rank #71 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-6 Astra scores higher in 5 categories and Qwen3.5 Max Preview in 3 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 30.8.

Side by side

GPT-6 AstraQwen3.5 Max Preview
ProviderOpenAIAlibaba (Qwen)
Noometry Index70.845.3
Released2026-09-03—
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked5617

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), Qwen3.5 Max Preview: 44.0 (#77)

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Coding14871487
DeepSWE74.1%—
FrontierCode53.3%—
LMArena WebDev1786—
FrontierSWE65.5%—
SciCode56.5%—
GSO79.4%—
WeirdML93.6%—
MirrorCode46.7%—
ALE-Bench2,951—

Agentic & Tool Use Not comparable

GPT-6 Astra: 52.9 (#3), Qwen3.5 Max Preview: —

BenchmarkGPT-6 AstraQwen3.5 Max Preview
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), Qwen3.5 Max Preview: 30.8 (#84)

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Hard Prompts14621483
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), Qwen3.5 Max Preview: 40.1 (#94)

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Math14651474
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), Qwen3.5 Max Preview: 41.8 (#107)

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Expert14831489
GPQA Diamond95.8%—
Humanity's Last Exam54.8%—
SimpleQA Verified75.6%—
Vectara Hallucination Rate8.7%—

Multimodal Not comparable

GPT-6 Astra: 55.0 (#3), Qwen3.5 Max Preview: —

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Vision1281—
Blueprint-Bench 249.7%—
Furniture Assembly80%—
LMArena Document1468—

Multilingual Qwen3.5 Max Preview leads

GPT-6 Astra: 53.7 (#61), Qwen3.5 Max Preview: 56.2 (#22)

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Non-English14301465
LMArena Chinese14841534
LMArena French14561484
LMArena German14401487
LMArena Japanese13791495
LMArena Korean14261438
LMArena Russian14361471
LMArena Spanish14071470

Instruction Following Too close to call

GPT-6 Astra: 76.3 (#44), Qwen3.5 Max Preview: 77.0 (#31)

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Instruction Following14501467

Long Context Too close to call

GPT-6 Astra: 44.5 (#62), Qwen3.5 Max Preview: 45.2 (#45)

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Longer Query14561476

Writing & Preference GPT-6 Astra leads

GPT-6 Astra: 75.3 (#7), Qwen3.5 Max Preview: 66.0 (#41)

BenchmarkGPT-6 AstraQwen3.5 Max Preview
LMArena Text14411470
LMArena Creative Writing14181464
LMArena Multi-Turn14481478
EQ-Bench Creative Writing2173—

Frequently asked questions

Is GPT-6 Astra better than Qwen3.5 Max Preview?

GPT-6 Astra is the stronger model overall, scoring 70.8 to 45.3 on the Noometry Index.

Is GPT-6 Astra or Qwen3.5 Max Preview better for coding?

GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 44.0 in the Noometry coding category.

How many benchmarks do GPT-6 Astra and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. GPT-6 Astra has 56 scored results on Noometry and Qwen3.5 Max Preview has 17.

Related comparisons

Go deeper