GPT-6 Luna vs GPT-5.6 Terra: Release Comparison

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Comparison of the GPT-6 Luna and GPT-5.6 Terra releases: 6 and 6 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 12 models.

For intelligence, GPT-5.6 Terra scores highest: GPT-5.6 Terra (Max) at 42, against GPT-6 Luna (Max) at 38 for GPT-6 Luna.
For output speed, GPT-6 Luna is fastest: GPT-6 Luna (Max) at 135 t/s, against GPT-5.6 Terra (Max) at 126 t/s for GPT-5.6 Terra.
For cost per task, GPT-6 Luna is cheapest: GPT-6 Luna (Low) at $0.0045, against GPT-5.6 Terra (Non-reasoning) at $0.14 for GPT-5.6 Terra.

Model Playground

Releases compared


	GPT-5.6 Terra (max)	GPT-6 Luna (max)	GPT-5.6 Terra (xhigh)	GPT-6 Luna (xhigh)	GPT-5.6 Terra (high)	GPT-6 Luna (high)	GPT-5.6 Terra (medium)	GPT-6 Luna (medium)	GPT-5.6 Terra (low)	GPT-6 Luna (low)	GPT-5.6 Terra (non-reasoning)	GPT-6 Luna (non-reasoning)
Intelligence Index	42	38	38	35	34	33	30	30	27	22	21	18
Finance & Accounting	41	40	40	37	37	36	32	33	30	24	21	20
Strategy & Ops	47	46	44	43	40	41	34	37	31	23	23	20
Legal	41	40	40	37	37	35	34	33	31	25	22	19
Healthcare & Medical	40	37	38	--	34	--	31	--	27	--	--	--
Engineering	43	37	38	34	34	32	31	29	28	23	21	21
Economics	45	45	44	42	42	40	37	37	34	30	24	24
AA-Briefcase v1.1	1334	1336	1333	1237	1202	1186	1039	1099	1014	741	947	903
GDPval-AA v2.1	1451	1432	1447	1364	1376	1340	1264	1262	1108	1033	1097	1045
AutomationBench-AA	59.6%	53.2%	47.1%	47.8%	42.0%	47.8%	33.5%	40.5%	29.1%	12.0%	12.5%	9.1%
Terminal-Bench 4.0	35.4%	12.6%	10.1%	8.1%	1.5%	4.5%	1.0%	2.5%	1.5%	0.0%	0.5%	1.5%
SciCode	55.0%	54.6%	52.3%	51.7%	52.4%	50.3%	50.5%	50.9%	49.9%	46.9%	45.1%	43.1%
Humanity's Last Exam	42.9%	38.5%	41.9%	34.3%	38.5%	32.9%	33.3%	28.3%	29.2%	20.3%	11.4%	8.6%
GDP.pdf	24.0%	22.8%	24.6%	18.6%	20.8%	18.2%	17.0%	13.8%	17.6%	9.0%	11.2%	5.8%
CritPt	30.0%	19.4%	27.1%	17.4%	22.9%	15.4%	17.4%	10.6%	9.4%	2.6%	2.0%	1.1%
AA-Omniscience	0	1	−3	−2	−3	−6	−5	−5	−7	−9	−23	−22
AA-LCR v1.1	83.0%	83.3%	79.0%	80.0%	77.7%	79.3%	74.0%	78.3%	71.3%	74.0%	58.7%	39.7%

Cost per TaskUSD	$1.40	$0.07	$0.63	$0.04	$0.34	$0.03	$0.18	$0.02	$0.14	$0.0045	$0.14	$0.01
Input PriceUSD/1M Tokens	$2.00	$0.10	$2.00	$0.10	$2.00	$0.10	$2.00	$0.10	$2.00	$0.10	$2.00	$0.10
Output PriceUSD/1M Tokens	$12.00	$0.50	$12.00	$0.50	$12.00	$0.50	$12.00	$0.50	$12.00	$0.50	$12.00	$0.50
Cache Hit PriceUSD/1M Tokens	$0.20	$0.01	$0.20	$0.01	$0.20	$0.01	$0.20	$0.01	$0.20	$0.01	$0.20	$0.01
Cache Write PriceUSD/1M Tokens	$2.50	$0.125	$2.50	$0.125	$2.50	$0.125	$2.50	$0.125	$2.50	$0.125	$2.50	$0.125

Output SpeedTokens/s	126	135	110	128	102	134	103	--	99	129	100	114
Time to First Tokens	131.32	116.77	43.03	37.04	7.36	23.45	1.75	--	1.43	2.52	0.69	0.88
Time to First Answer Tokens	131.32	116.77	43.03	37.04	7.36	23.45	1.75	--	1.43	2.52	0.69	0.88
End-to-End Response Times	135.30	120.48	47.56	40.94	12.27	27.19	6.63	--	6.47	6.39	5.67	5.26
Time per Tasks	307.79	368.29	179.96	210.38	109.99	148.09	54.09	--	38.09	16.55	31.13	32.88

Context Window	1M	1M	1M	1M	1M	1M	1M	1M	1M	1M	1M	1M
Creator	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI
License	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary
Input Modality	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image
Output Modality	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text
Providers

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

GPT-6 Luna

GPT-5.6 Terra

Pareto line

AA-Briefcase v1.1

GDPval-AA v2.1

Cost per Task (USD, Log Scale)

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Speed & Latency

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Capability Scores

Capability Indexes

Measures the performance of models on specific capabilities and industries

Finance & Accounting Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 6 evaluations: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better

Economics Index

Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better

GPT-6 Luna vs GPT-5.6 Terra: Release Comparison

Intelligence

Speed

Cost per Task

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Cost

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Speed & Latency

Output Speed

Output Speed

Model Performance Representation

Capability Scores

Capability Indexes