Noometry

Model comparison

GPT-5.5 Instant vs GPT-5.6 Luna

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 42.7 on the Noometry Index.

Last verified . 27 shared benchmarks.

GPT-5.5 Instant OpenAI

42.7

Rank #110 Confirmed

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-5.5 Instant scores higher in 0 categories and GPT-5.6 Luna in 9 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 26.5.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 2.4% for GPT-5.5 Instant and 61% for GPT-5.6 Luna.

Side by side

GPT-5.5 InstantGPT-5.6 Luna
ProviderOpenAIOpenAI
Noometry Index42.754.6
Released2026-05-052026-07-09
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$0.20
Output $ / M tokens—$1.20
Results tracked2752

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

Category by category

Coding GPT-5.6 Luna leads

GPT-5.5 Instant: 44.3 (#74), GPT-5.6 Luna: 54.5 (#28)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
SciCode48.6%53.6%
LMArena Coding14331466
DeepSWE—67.2%
FrontierCode—39.8%
CursorBench—35.9%
LMArena WebDev—1519
WeirdML—60.9%
ALE-Bench—1,667

Agentic & Tool Use Not comparable

GPT-5.5 Instant: —, GPT-5.6 Luna: 34.4 (#45)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
APEX-Agents—43%
BALROG—45.6%
GDP.pdf—22.7%
Vending-Bench 2—4,095

Reasoning GPT-5.6 Luna leads

GPT-5.5 Instant: 24.9 (#155), GPT-5.6 Luna: 47.6 (#43)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
CritPt0%20.6%
Chess Puzzles12%40%
LMArena Hard Prompts14261451
Epoch Capabilities Index142.52156.39
ARC-AGI-2—59.5%
SimpleBench—46.8%
Kagi LLM Benchmark—49.1%
NYT Connections (extended)—69.4%
ARC-AGI-1—88%
Mystery Game Puzzles—21%
DTBench—89.1%
LMCA—48.5%
Surface Evolver Bench—61.9%

Math GPT-5.6 Luna leads

GPT-5.5 Instant: 26.5 (#259), GPT-5.6 Luna: 77.7 (#14)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
FrontierMath (Tiers 1-3)26.3%82.1%
FrontierMath Tier 42.4%61%
OTIS Mock AIME 2024-202568.1%98.3%
LMArena Math14201458
ProofBench—60%

Knowledge GPT-5.6 Luna leads

GPT-5.5 Instant: 48.9 (#74), GPT-5.6 Luna: 58.5 (#34)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
GPQA Diamond82.5%91.6%
LMArena Expert14091478
SimpleQA Verified—41%

Multimodal GPT-5.6 Luna leads

GPT-5.5 Instant: 40.0 (#52), GPT-5.6 Luna: 42.7 (#28)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
LMArena Vision12501258
LMArena Document14031457
Blueprint-Bench 2—22.6%
Furniture Assembly—42.5%

Multilingual Too close to call

GPT-5.5 Instant: 52.8 (#80), GPT-5.6 Luna: 52.8 (#78)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
LMArena Non-English14171417
LMArena Chinese14561470
LMArena French14281456
LMArena German14111454
LMArena Japanese14081411
LMArena Korean13921415
LMArena Russian14311428
LMArena Spanish14291448

Instruction Following GPT-5.6 Luna leads

GPT-5.5 Instant: 74.2 (#100), GPT-5.6 Luna: 75.6 (#57)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
LMArena Instruction Following14061437

Long Context Too close to call

GPT-5.5 Instant: 43.4 (#96), GPT-5.6 Luna: 43.9 (#82)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
LMArena Longer Query14221436

Writing & Preference GPT-5.6 Luna leads

GPT-5.5 Instant: 61.8 (#85), GPT-5.6 Luna: 68.0 (#29)

BenchmarkGPT-5.5 InstantGPT-5.6 Luna
LMArena Text14191431
LMArena Creative Writing14191396
LMArena Multi-Turn14331434
EQ-Bench Creative Writing—1829
EQ-Bench 4—1156

Frequently asked questions

Is GPT-5.5 Instant better than GPT-5.6 Luna?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 42.7 on the Noometry Index.

Is GPT-5.5 Instant or GPT-5.6 Luna better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 44.3 in the Noometry coding category.

How many benchmarks do GPT-5.5 Instant and GPT-5.6 Luna share?

27 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and GPT-5.6 Luna has 52.

Related comparisons

Go deeper