Model comparison

GPT-6 Luna vs GPT-6 Sol

GPT-6 Sol is the stronger model overall, scoring 49.2 to 45.1 on the Noometry Index. GPT-6 Luna costs 20× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.

Last verified October 10, 2026. 18 shared benchmarks.

GPT-6 Luna OpenAI

45.1

Rank #65 Confirmed

GPT-6 Sol OpenAI

49.2

Rank #46 Confirmed

Summary

They share 18 benchmarks with published results for both. GPT-6 Luna scores higher in 3 categories and GPT-6 Sol in 6 categories; 5 gaps are clear of the uncertainty.
The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 31.7.
The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 90.1% for GPT-6 Sol.
GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $2 / $10 for GPT-6 Sol.

Side by side

GPT-6 Luna and GPT-6 Sol specifications
	GPT-6 Luna	GPT-6 Sol
Provider	OpenAI	OpenAI
Noometry Index	45.1	49.2
Released	2026-09-22	2026-09-22
Weights	Proprietary	Proprietary
Context window	1.05M	1.05M
Max output	128K	128K
Input $ / M tokens	$0.10	$2
Output $ / M tokens	$0.50	$10
Results tracked	18	22

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

Category by category

Coding GPT-6 Sol leads

GPT-6 Luna: 54.7 (#24), GPT-6 Sol: 59.6 (#11)

Coding benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
DeepSWE	66.6%	68.8%
FrontierCode	42.4%	49.3%
LMArena WebDev	1583	1692
LMArena Coding	1448	1453

Agentic & Tool Use Not comparable

GPT-6 Luna: —, GPT-6 Sol: 33.5 (#49)

Agentic & Tool Use benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
GDP.pdf	—	28%

Reasoning GPT-6 Sol leads

GPT-6 Luna: 31.7 (#68), GPT-6 Sol: 49.3 (#34)

Reasoning benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
NYT Connections (extended)	68.7%	90.1%
LMArena Hard Prompts	1415	1420
EBR-Bench	—	53.3%

Math Too close to call

GPT-6 Luna: 35.6 (#140), GPT-6 Sol: 35.8 (#135)

Math benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
LMArena Math	1396	1404

Knowledge GPT-6 Sol leads

GPT-6 Luna: 40.1 (#110), GPT-6 Sol: 43.0 (#87)

Knowledge benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
LMArena Expert	1458	1449
Vectara Hallucination Rate	—	6.5%

Multimodal GPT-6 Sol leads

GPT-6 Luna: 42.0 (#27), GPT-6 Sol: 47.6 (#9)

Multimodal benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
Furniture Assembly	44.2%	58.3%

Multilingual Too close to call

GPT-6 Luna: 51.0 (#111), GPT-6 Sol: 51.0 (#113)

Multilingual benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
LMArena Non-English	1390	1389
LMArena Chinese	1425	1416
LMArena Russian	1392	1407
LMArena Spanish	1416	1377

Instruction Following Too close to call

GPT-6 Luna: 74.7 (#85), GPT-6 Sol: 74.4 (#97)

Instruction Following benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
LMArena Instruction Following	1414	1406

Long Context Too close to call

GPT-6 Luna: 43.3 (#95), GPT-6 Sol: 43.2 (#100)

Long Context benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
LMArena Longer Query	1417	1415

Writing & Preference GPT-6 Sol leads

GPT-6 Luna: 58.4 (#115), GPT-6 Sol: 72.3 (#15)

Writing & Preference benchmarks
Benchmark	GPT-6 Luna	GPT-6 Sol
LMArena Text	1392	1396
LMArena Creative Writing	1357	1392
LMArena Multi-Turn	1400	1405
EQ-Bench Creative Writing	—	2125

Frequently asked questions

Is GPT-6 Luna better than GPT-6 Sol?

Which is cheaper, GPT-6 Luna or GPT-6 Sol?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GPT-6 Sol lists at $2 and $10.

Is GPT-6 Luna or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 54.7 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do GPT-6 Luna and GPT-6 Sol share?

18 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and GPT-6 Sol has 22.