Model comparison

DeepSeek-V3.1 vs GPT-6 Luna

GPT-6 Luna is the stronger model overall, scoring 45.1 to 42.2 on the Noometry Index.

Last verified October 10, 2026. 13 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.2

Rank #106 Confirmed

GPT-6 Luna OpenAI

45.1

Rank #65 Confirmed

Summary

They share 13 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 4 categories and GPT-6 Luna in 4 categories; 5 gaps are clear of the uncertainty.
The widest gap is in coding, where GPT-6 Luna leads 54.7 to 39.8.
GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
GPT-6 Luna accepts more context: 1.05M tokens versus 164K.
DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1 and GPT-6 Luna specifications
	DeepSeek-V3.1	GPT-6 Luna
Provider	DeepSeek	OpenAI
Noometry Index	42.2	45.1
Released	2025-08-21	2026-09-22
Weights	Open	Proprietary
Context window	164K	1.05M
Max output	8K	128K
Input $ / M tokens	$0.25	$0.10
Output $ / M tokens	$0.95	$0.50
Results tracked	27	18

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

Category by category

Coding GPT-6 Luna leads

DeepSeek-V3.1: 39.8 (#140), GPT-6 Luna: 54.7 (#24)

Coding benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
LMArena Coding	1417	1448
DeepSWE	—	66.6%
FrontierCode	—	42.4%
LMArena WebDev	—	1583
WeirdML	38.4%	—

Reasoning GPT-6 Luna leads

DeepSeek-V3.1: 27.3 (#109), GPT-6 Luna: 31.7 (#68)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
LMArena Hard Prompts	1417	1415
SimpleBench	40%	—
Kagi LLM Benchmark	53.2%	—
NYT Connections (extended)	—	68.7%
DTBench	82.7%	—
LMCA	24.3%	—
Epoch Capabilities Index	139.92	—
ForecastBench	58	—

Math Too close to call

DeepSeek-V3.1: 36.1 (#125), GPT-6 Luna: 35.6 (#140)

Math benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
LMArena Math	1420	1396

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.0 (#86), GPT-6 Luna: 40.1 (#110)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
LMArena Expert	1403	1458
Vectara Hallucination Rate	5.5%	—

Multimodal Not comparable

DeepSeek-V3.1: —, GPT-6 Luna: 42.0 (#27)

Multimodal benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
Furniture Assembly	—	44.2%

Multilingual Too close to call

DeepSeek-V3.1: 51.8 (#100), GPT-6 Luna: 51.0 (#111)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
LMArena Non-English	1400	1390
LMArena Chinese	1470	1425
LMArena Russian	1405	1392
LMArena Spanish	1429	1416
LMArena French	1447	—
LMArena German	1412	—
LMArena Japanese	1374	—
LMArena Korean	1337	—

Instruction Following Too close to call

DeepSeek-V3.1: 74.1 (#105), GPT-6 Luna: 74.7 (#85)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
LMArena Instruction Following	1400	1414

Long Context GPT-6 Luna leads

DeepSeek-V3.1: 36.3 (#227), GPT-6 Luna: 43.3 (#95)

Long Context benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
LMArena Longer Query	1422	1417
Fiction.LiveBench	52.8%	—

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.5 (#93), GPT-6 Luna: 58.4 (#115)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	GPT-6 Luna
LMArena Text	1420	1392
LMArena Creative Writing	1401	1357
LMArena Multi-Turn	1408	1400
EQ-Bench Creative Writing	1436	—

Frequently asked questions

Is DeepSeek-V3.1 better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 42.2 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or GPT-6 Luna?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.

Is DeepSeek-V3.1 or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 39.8 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 164K.

How many benchmarks do DeepSeek-V3.1 and GPT-6 Luna share?

13 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GPT-6 Luna has 18.