GPT-6 Luna vs Gemini 3.8 Flash: Release Comparison

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

Comparison of the GPT-6 Luna and Gemini 3.8 Flash releases: 6 and 3 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 9 models.

For intelligence, Gemini 3.8 Flash scores highest: Gemini 3.8 Flash (High) at 31, against GPT-6 Luna (Max) at 28 for GPT-6 Luna.
For output speed, Gemini 3.8 Flash is fastest: Gemini 3.8 Flash (High) at 131 t/s, against GPT-6 Luna (Xhigh) at 127 t/s for GPT-6 Luna.
For cost per task, GPT-6 Luna is cheapest: GPT-6 Luna (Low) at $0.01, against Gemini 3.8 Flash (Medium) at $6.26 for Gemini 3.8 Flash.

Model Playground

Releases compared


	Gemini 3.8 Flash (high)	Gemini 3.8 Flash (medium)	GPT-6 Luna (max)	GPT-6 Luna (xhigh)	Gemini 3.8 Flash (low)	GPT-6 Luna (high)	GPT-6 Luna (medium)	GPT-6 Luna (low)	GPT-6 Luna (non-reasoning)
Intelligence Index	31	30	28	23	22	21	18	10	9
Finance & Accounting	42	42	34	31	34	29	26	17	19
Strategy & Ops	47	47	43	39	35	38	34	17	17
Legal	42	42	32	28	33	27	24	16	17
Healthcare & Medical	38	38	35	30	31	29	27	16	16
Engineering	38	37	33	29	31	27	25	19	17
Economics	41	40	35	32	34	30	28	19	20
AA-Briefcase v1.1	1203	1183	1337	1235	1062	1187	1096	740	902
AutomationBench-AA	59.9%	60.9%	53.2%	47.8%	36.5%	47.8%	40.5%	12.0%	9.1%
Terminal-Bench 4.0	19.7%	19.7%	12.6%	8.1%	10.1%	4.5%	2.5%	0.0%	1.5%
FrontierCode 2.0	18.7%	16.5%	25.2%	18.4%	8.1%	18.6%	12.8%	2.2%	1.6%
AA-Omniscience v1.1	23	24	−8	−13	13	−13	−14	−18	−26
GDP.pdf	21.0%	22.8%	22.8%	18.6%	18.6%	18.2%	13.8%	9.0%	5.8%
HLE-Diamond	33.1%	29.1%	22.2%	18.9%	24.3%	15.6%	15.1%	10.2%	6.3%
CritPt v2 (Hard Subset)	43.5%	44.0%	41.5%	35.5%	31.5%	30.5%	26.0%	9.5%	4.5%
Terminal-Bench-Science 0.1	10.0%	10.5%	8.6%	5.2%	8.1%	2.9%	1.4%	1.0%	1.0%

Cost per TaskUSD	$7.77	$6.26	$0.15	$0.10	--	$0.07	$0.04	$0.01	$0.07
Input PriceUSD/1M Tokens	$0.75	$0.75	$0.10	$0.10	$0.75	$0.10	$0.10	$0.10	$0.10
Output PriceUSD/1M Tokens	$3.75	$3.75	$0.50	$0.50	$3.75	$0.50	$0.50	$0.50	$0.50
Cache Hit PriceUSD/1M Tokens	$0.075	$0.075	$0.01	$0.01	$0.075	$0.01	$0.01	$0.01	$0.01
Cache Write PriceUSD/1M Tokens	$0.75	$0.75	$0.125	$0.125	$0.75	$0.125	$0.125	$0.125	$0.125

Output SpeedTokens/s	131	--	117	127	--	119	--	121	112
Time to First Tokens	24.89	--	112.81	40.38	--	29.02	--	2.81	0.81
Time to First Answer Tokens	24.89	--	112.81	40.38	--	29.02	--	2.81	0.81
End-to-End Response Times	28.71	--	117.08	44.30	--	33.22	--	6.96	5.29
Time per Tasks	740.45	--	645.09	345.72	--	276.77	--	27.05	89.95

Context Window	1M	1M	1M	1M	1M	1M	1M	1M	1M
Creator	Google	Google	OpenAI	OpenAI	Google	OpenAI	OpenAI	OpenAI	OpenAI
License	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary
Input Modality	Supports: text, image, speech, and video	Supports: text, image, speech, and video	Supports: text and image	Supports: text and image	Supports: text, image, speech, and video	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
Providers

Updated

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

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index v5.0 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Cost per Task

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

Most attractive quadrant

GPT-6 Luna

Gemini 3.8 Flash

Pareto line

AA-Briefcase v1.1

AutomationBench-AA

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 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 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better

Engineering Index

Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode 2.0, AA-Briefcase v1.1 · Higher is better

Economics Index

Incorporates 4 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, GDP.pdf · Higher is better

Benchmarks

AA-PersonalityBenchNew

Model AvsModel B

AA-PersonalityBench: Expressiveness Index, GPT-6 Luna (max) vs Gemini 3.8 Flash (high)

Chance each model’s answer is judged to show more of each trait from their Elo gap · 50% is an even match

GPT-6 Luna (max)

Gemini 3.8 Flash (high)

Metaphorical

99%

Natural Sounding

92%

Eloquent

92%

Lexically Varied

11%

89%

Literate

53%

47%

GPT-6 Luna vs Gemini 3.8 Flash: Release Comparison

Intelligence

Speed

Cost per Task

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. Cost per 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

Benchmarks

AA-PersonalityBenchNew

AA-PersonalityBench: Expressiveness Index, GPT-6 Luna (max) vs Gemini 3.8 Flash (high)