Noometry

Model comparison

GPT-6 Luna vs Trinity Large Thinking

GPT-6 Luna is the stronger model overall, scoring 53.3 to 38.6 on the Noometry Index.

Last verified . 21 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Trinity Large Thinking Arcee AI

38.6

Rank #185 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 37.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 16.5% for Trinity Large Thinking.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 262K.
  • Trinity Large Thinking has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaTrinity Large Thinking
ProviderOpenAIArcee AI
Noometry Index53.338.6
Released2026-09-222026-04-01
WeightsProprietaryOpen
Context window1.05M262K
Max output128K80K
Input $ / M tokens$0.10$0.25
Output $ / M tokens$0.50$0.80
Results tracked4224

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), Trinity Large Thinking: 34.1 (#244)

BenchmarkGPT-6 LunaTrinity Large Thinking
LMArena WebDev15811238
SciCode54.6%36.1%
LMArena Coding14391381
DeepSWE66.6%—
FrontierCode42.4%—
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), Trinity Large Thinking: —

BenchmarkGPT-6 LunaTrinity Large Thinking
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Trinity Large Thinking: 16.9 (#298)

BenchmarkGPT-6 LunaTrinity Large Thinking
NYT Connections (extended)68.7%16.5%
CritPt19.4%0.9%
LMArena Hard Prompts14111350
ARC-AGI-259.3%—
ARC-AGI-186.7%—
Chess Puzzles31%—
Thematic Generalization—41.6%
Mystery Game Puzzles7%—
DTBench90.1%—
LMCA44.5%—
Surface Evolver Bench—15.6%
Epoch Capabilities Index156.28—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Trinity Large Thinking: 37.6 (#149)

BenchmarkGPT-6 LunaTrinity Large Thinking
LMArena Math14161366
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), Trinity Large Thinking: 40.9 (#113)

BenchmarkGPT-6 LunaTrinity Large Thinking
LMArena Expert14441360
GPQA Diamond90.5%—
SimpleQA Verified41.4%—
Vectara Hallucination Rate—6.9%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Trinity Large Thinking: —

BenchmarkGPT-6 LunaTrinity Large Thinking
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Trinity Large Thinking: 46.2 (#160)

BenchmarkGPT-6 LunaTrinity Large Thinking
LMArena Non-English13861325
LMArena Chinese14331373
LMArena French14201374
LMArena German13691356
LMArena Japanese13691311
LMArena Korean13601306
LMArena Russian13941337
LMArena Spanish13931357

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Trinity Large Thinking: 70.5 (#162)

BenchmarkGPT-6 LunaTrinity Large Thinking
LMArena Instruction Following14091334

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Trinity Large Thinking: 41.3 (#144)

BenchmarkGPT-6 LunaTrinity Large Thinking
LMArena Longer Query14091355

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Trinity Large Thinking: 53.8 (#158)

BenchmarkGPT-6 LunaTrinity Large Thinking
LMArena Text13911340
LMArena Creative Writing13631320
LMArena Multi-Turn13961342

Frequently asked questions

Is GPT-6 Luna better than Trinity Large Thinking?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 38.6 on the Noometry Index.

Which is cheaper, GPT-6 Luna or Trinity Large Thinking?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.

Is GPT-6 Luna or Trinity Large Thinking better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 34.1 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 262K.

How many benchmarks do GPT-6 Luna and Trinity Large Thinking share?

21 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Trinity Large Thinking has 24.

Related comparisons

Go deeper