Noometry

Model comparison

GPT-6 Luna vs Hy4 preview

GPT-6 Luna is the stronger model overall, scoring 53.3 to 45.3 on the Noometry Index.

Last verified . 3 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Hy4 preview Tencent

45.3

Rank #73 Reported

Summary

  • They share 3 benchmarks with published results for both. GPT-6 Luna scores higher in 3 categories and Hy4 preview in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 55.7.
  • The biggest single-benchmark swing is ProofBench: 64% for GPT-6 Luna and 75% for Hy4 preview.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 1.05M.
  • Hy4 preview has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaHy4 preview
ProviderOpenAITencent
Noometry Index53.345.3
Released2026-09-222026-08-28
WeightsProprietaryOpen
Context window1.05M1.05M
Max output128K64K
Input $ / M tokens$0.10$0.83
Output $ / M tokens$0.50$2.50
Results tracked423

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), Hy4 preview: 51.6 (#38)

BenchmarkGPT-6 LunaHy4 preview
LMArena WebDev15811632
DeepSWE66.6%—
FrontierCode42.4%—
SciCode54.6%—
LMArena Coding1439—
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), Hy4 preview: —

BenchmarkGPT-6 LunaHy4 preview
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Hy4 preview: 31.9 (#79)

BenchmarkGPT-6 LunaHy4 preview
NYT Connections (extended)68.7%68.2%
ARC-AGI-259.3%—
ARC-AGI-186.7%—
CritPt19.4%—
Chess Puzzles31%—
LMArena Hard Prompts1411—
Mystery Game Puzzles7%—
DTBench90.1%—
LMCA44.5%—
Epoch Capabilities Index156.28—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Hy4 preview: 55.7 (#42)

BenchmarkGPT-6 LunaHy4 preview
ProofBench64%75%
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
OTIS Mock AIME 2024-202598.9%—
LMArena Math1416—

Knowledge Not comparable

GPT-6 Luna: 57.0 (#41), Hy4 preview: —

BenchmarkGPT-6 LunaHy4 preview
GPQA Diamond90.5%—
SimpleQA Verified41.4%—
LMArena Expert1444—

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Hy4 preview: —

BenchmarkGPT-6 LunaHy4 preview
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual Not comparable

GPT-6 Luna: 50.5 (#117), Hy4 preview: —

BenchmarkGPT-6 LunaHy4 preview
LMArena Non-English1386—
LMArena Chinese1433—
LMArena French1420—
LMArena German1369—
LMArena Japanese1369—
LMArena Korean1360—
LMArena Russian1394—
LMArena Spanish1393—

Instruction Following Not comparable

GPT-6 Luna: 74.3 (#99), Hy4 preview: —

BenchmarkGPT-6 LunaHy4 preview
LMArena Instruction Following1409—

Long Context Not comparable

GPT-6 Luna: 43.0 (#111), Hy4 preview: —

BenchmarkGPT-6 LunaHy4 preview
LMArena Longer Query1409—

Writing & Preference Not comparable

GPT-6 Luna: 58.3 (#119), Hy4 preview: —

BenchmarkGPT-6 LunaHy4 preview
LMArena Text1391—
LMArena Creative Writing1363—
LMArena Multi-Turn1396—

Frequently asked questions

Is GPT-6 Luna better than Hy4 preview?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 45.3 on the Noometry Index.

Which is cheaper, GPT-6 Luna or Hy4 preview?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Hy4 preview lists at $0.83 and $2.50.

Is GPT-6 Luna or Hy4 preview better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 51.6 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 1.05M.

How many benchmarks do GPT-6 Luna and Hy4 preview share?

3 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Hy4 preview has 3.

Related comparisons

Go deeper