Noometry

Model comparison

GPT-6 Luna vs Qwen1.5 4b Chat

GPT-6 Luna is the stronger model overall, scoring 53.3 to 28.8 on the Noometry Index.

Last verified . 13 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Qwen1.5 4b Chat Alibaba (Qwen)

28.8

Rank #322 Confirmed

Summary

  • They share 13 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and Qwen1.5 4b Chat in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 30.4.
  • Qwen1.5 4b Chat has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaQwen1.5 4b Chat
ProviderOpenAIAlibaba (Qwen)
Noometry Index53.328.8
Released2026-09-22—
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4213

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

Category by category

Coding GPT-6 Luna leads

GPT-6 Luna: 55.5 (#25), Qwen1.5 4b Chat: 29.1 (#308)

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Coding1439999
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1581—
SciCode54.6%—
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), Qwen1.5 4b Chat: —

BenchmarkGPT-6 LunaQwen1.5 4b Chat
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Qwen1.5 4b Chat: 18.5 (#279)

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Hard Prompts1411976
ARC-AGI-259.3%—
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
CritPt19.4%—
Chess Puzzles31%—
Mystery Game Puzzles7%—
DTBench90.1%—
LMCA44.5%—
Epoch Capabilities Index156.28—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Qwen1.5 4b Chat: 30.4 (#234)

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Math14161026
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
OTIS Mock AIME 2024-202598.9%—
ProofBench64%—

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Qwen1.5 4b Chat: 26.7 (#255)

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Expert1444980
GPQA Diamond90.5%—
SimpleQA Verified41.4%—

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Qwen1.5 4b Chat: —

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Qwen1.5 4b Chat: 24.1 (#290)

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Non-English1386979
LMArena Chinese14331024
LMArena German1369902
LMArena Russian1394952
LMArena French1420—
LMArena Japanese1369—
LMArena Korean1360—
LMArena Spanish1393—

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Qwen1.5 4b Chat: 49.0 (#300)

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Instruction Following1409978

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Qwen1.5 4b Chat: 30.1 (#290)

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Longer Query1409988

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Qwen1.5 4b Chat: 23.8 (#309)

BenchmarkGPT-6 LunaQwen1.5 4b Chat
LMArena Text1391997
LMArena Creative Writing1363969
LMArena Multi-Turn1396977

Frequently asked questions

Is GPT-6 Luna better than Qwen1.5 4b Chat?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 28.8 on the Noometry Index.

Is GPT-6 Luna or Qwen1.5 4b Chat better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 29.1 in the Noometry coding category.

How many benchmarks do GPT-6 Luna and Qwen1.5 4b Chat share?

13 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Qwen1.5 4b Chat has 13.

Related comparisons

Go deeper