GPT-6 Luna vs Qwen3.8 27B: Release Comparison

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

Comparison of the GPT-6 Luna and Qwen3.8 27B releases: 6 and 4 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 10 models.

For intelligence, GPT-6 Luna scores highest: GPT-6 Luna (Max) at 28, against Qwen3.8 27B (Xhigh) at 20 for Qwen3.8 27B.
For output speed, GPT-6 Luna is fastest: GPT-6 Luna (Xhigh) at 127 t/s, against Qwen3.8 27B (Medium) at 51 t/s for Qwen3.8 27B.
For cost per task, GPT-6 Luna is cheapest: GPT-6 Luna (Low) at $0.01, against Qwen3.8 27B (Low) at $1.91 for Qwen3.8 27B.

Model Playground

Releases compared


	GPT-6 Luna (max)	GPT-6 Luna (xhigh)	GPT-6 Luna (high)	Qwen3.8 27B (xhigh)	GPT-6 Luna (medium)	Qwen3.8 27B (medium)	Qwen3.8 27B (low)	Qwen3.8 27B (non-reasoning)	GPT-6 Luna (low)	GPT-6 Luna (non-reasoning)
Intelligence Index	28	23	21	20	18	17	16	10	10	9
Finance & Accounting	34	31	29	36	26	29	28	22	17	19
Strategy & Ops	43	39	38	39	34	34	29	16	17	17
Legal	32	28	27	33	24	26	27	22	16	17
Healthcare & Medical	35	30	29	35	27	24	23	19	16	16
Engineering	33	29	27	28	25	22	21	17	19	17
Economics	35	32	30	35	28	29	28	22	19	20
AA-Briefcase v1.1	1337	1235	1187	1393	1096	1373	1270	901	740	902
AutomationBench-AA	53.2%	47.8%	47.8%	48.2%	40.5%	40.3%	30.1%	12.4%	12.0%	9.1%
Terminal-Bench 4.0	12.6%	8.1%	4.5%	5.6%	2.5%	5.1%	2.5%	0.0%	0.0%	1.5%
FrontierCode 2.0	25.2%	18.4%	18.6%	14.9%	12.8%	11.5%	12.4%	3.7%	2.2%	1.6%
AA-Omniscience v1.1	−8	−13	−13	−6	−14	−36	−21	−7	−18	−26
GDP.pdf	22.8%	18.6%	18.2%	16.4%	13.8%	12.8%	10.4%	5.2%	9.0%	5.8%
HLE-Diamond	22.2%	18.9%	15.6%	15.3%	15.1%	6.7%	6.8%	4.2%	10.2%	6.3%
CritPt v2 (Hard Subset)	41.5%	35.5%	30.5%	4.0%	26.0%	16.5%	5.5%	2.0%	9.5%	4.5%
Terminal-Bench-Science 0.1	8.6%	5.2%	2.9%	0.5%	1.4%	1.0%	0.5%	0.0%	1.0%	1.0%

Cost per TaskUSD	$0.15	$0.10	$0.07	$3.53	$0.04	$2.16	$1.91	$3.77	$0.01	$0.07
Input PriceUSD/1M Tokens	$0.10	$0.10	$0.10	$0.50	$0.10	$0.50	$0.50	$0.50	$0.10	$0.10
Output PriceUSD/1M Tokens	$0.50	$0.50	$0.50	$3.00	$0.50	$3.00	$3.00	$3.00	$0.50	$0.50
Cache Hit PriceUSD/1M Tokens	$0.01	$0.01	$0.01	$0.10	$0.01	$0.10	$0.10	$0.10	$0.01	$0.01
Cache Write PriceUSD/1M Tokens	$0.125	$0.125	$0.125	--	$0.125	--	--	--	$0.125	$0.125

Output SpeedTokens/s	117	127	119	41	--	51	48	46	121	112
Time to First Tokens	112.81	40.38	29.02	4.01	--	4.08	3.93	3.96	2.81	0.81
Time to First Answer Tokens	112.81	40.38	29.02	52.66	--	43.22	45.40	3.96	2.81	0.81
End-to-End Response Times	117.08	44.30	33.22	64.83	--	53.01	55.77	14.85	6.96	5.29
Time per Tasks	645.09	345.72	276.77	1,828.14	--	1,579.30	1,414.67	870.08	27.05	89.95

Context Window	1M	1M	1M	256k	1M	256k	256k	256k	1M	1M
Creator	OpenAI	OpenAI	OpenAI	Alibaba	OpenAI	Alibaba	Alibaba	Alibaba	OpenAI	OpenAI
License	Proprietary	Proprietary	Proprietary	Open	Proprietary	Open	Open	Open	Proprietary	Proprietary
Input Modality	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text, image, and video	Supports: text and image	Supports: text, image, and video	Supports: text, image, and video	Supports: text, image, and video	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
Providers				+7				+4

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

Qwen3.8 27B

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 Qwen3.8 27B (xhigh)

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)

Qwen3.8 27B (xhigh)

Natural Sounding

93%

Lexically Varied

90%

10%

Literate

85%

15%

Metaphorical

16%

84%

Eloquent

40%

60%

GPT-6 Luna vs Qwen3.8 27B: 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 Qwen3.8 27B (xhigh)