Model comparison

DeepSeek-V3.1-Terminus vs GPT-6 Luna

GPT-6 Luna is the stronger model overall, scoring 53.3 to 43.1 on the Noometry Index.

Last verified October 12, 2026. 15 shared benchmarks.

DeepSeek-V3.1-Terminus

DeepSeek

43.1

Rank #97 Confirmed

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Summary

They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 3 categories and GPT-6 Luna in 4 categories; 5 gaps are clear of the uncertainty.
The widest gap is in math, where GPT-6 Luna leads 76.1 to 38.5.
The biggest single-benchmark swing is CritPt: 1.7% for DeepSeek-V3.1-Terminus and 19.4% for GPT-6 Luna.
GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.27 / $1 for DeepSeek-V3.1-Terminus.
GPT-6 Luna accepts more context: 1.05M tokens versus 164K.
DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1-Terminus and GPT-6 Luna specifications
	DeepSeek-V3.1-Terminus	GPT-6 Luna
Provider	DeepSeek	OpenAI
Noometry Index	43.1	53.3
Released	2025-09-22	2026-09-22
Weights	Open	Proprietary
Context window	164K	1.05M
Max output	147K	128K
Input $ / M tokens	$0.27	$0.10
Output $ / M tokens	$1	$0.50
Results tracked	16	42

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

Category by category

Coding GPT-6 Luna leads

DeepSeek-V3.1-Terminus: 42.0 (#113), GPT-6 Luna: 55.5 (#25)

Coding benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
SciCode	40.6%	54.6%
LMArena Coding	1426	1439
ALE-Bench	745.17	1,577
DeepSWE	—	66.6%
FrontierCode	—	42.4%
LMArena WebDev	—	1581

Agentic & Tool Use Not comparable

DeepSeek-V3.1-Terminus: —, GPT-6 Luna: 33.3 (#54)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
APEX-Agents	—	44.3%
GDP.pdf	—	23%

Reasoning GPT-6 Luna leads

DeepSeek-V3.1-Terminus: 26.4 (#133), GPT-6 Luna: 48.2 (#41)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
CritPt	1.7%	19.4%
LMArena Hard Prompts	1426	1411
DTBench	81.3%	90.1%
LMCA	28.6%	44.5%
ARC-AGI-2	—	59.3%
Kagi LLM Benchmark	57.4%	—
NYT Connections (extended)	—	68.7%
ARC-AGI-1	—	86.7%
Chess Puzzles	—	31%
Mystery Game Puzzles	—	7%
Epoch Capabilities Index	—	156.28

Math GPT-6 Luna leads

DeepSeek-V3.1-Terminus: 38.5 (#137), GPT-6 Luna: 76.1 (#15)

Math benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
LMArena Math	1402	1416
FrontierMath (Tiers 1-3)	—	78.9%
FrontierMath Tier 4	—	56.1%
OTIS Mock AIME 2024-2025	—	98.9%
ProofBench	—	64%

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, GPT-6 Luna: 57.0 (#41)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
GPQA Diamond	—	90.5%
SimpleQA Verified	—	41.4%
LMArena Expert	—	1444

Multimodal Not comparable

DeepSeek-V3.1-Terminus: —, GPT-6 Luna: 42.4 (#30)

Multimodal benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
LMArena Vision	—	1217
Blueprint-Bench 2	—	31.2%
Furniture Assembly	—	44.2%

Multilingual DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 52.1 (#92), GPT-6 Luna: 50.5 (#117)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
LMArena Non-English	1407	1386
LMArena Russian	1436	1394
LMArena Chinese	—	1433
LMArena French	—	1420
LMArena German	—	1369
LMArena Japanese	—	1369
LMArena Korean	—	1360
LMArena Spanish	—	1393

Instruction Following Too close to call

DeepSeek-V3.1-Terminus: 74.0 (#106), GPT-6 Luna: 74.3 (#99)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
LMArena Instruction Following	1404	1409

Long Context Too close to call

DeepSeek-V3.1-Terminus: 43.4 (#97), GPT-6 Luna: 43.0 (#111)

Long Context benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
LMArena Longer Query	1421	1409

Writing & Preference DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 61.0 (#92), GPT-6 Luna: 58.3 (#119)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1-Terminus	GPT-6 Luna
LMArena Text	1419	1391
LMArena Creative Writing	1403	1363
LMArena Multi-Turn	1411	1396

Frequently asked questions

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

GPT-6 Luna is the stronger model overall, scoring 53.3 to 43.1 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1-Terminus 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-Terminus lists at $0.27 and $1.

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

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 42.0 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-Terminus and GPT-6 Luna share?

15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GPT-6 Luna has 42.