GPT-6 Astra vs gpt-oss-120b: Release Comparison

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

Comparison of the GPT-6 Astra and gpt-oss-120b releases: 5 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 7 models.

For intelligence, GPT-6 Astra scores highest: GPT-6 Astra (Max) at 57, against gpt-oss-120b (High) at 4 for gpt-oss-120b.
For time per task, GPT-6 Astra is fastest: GPT-6 Astra (Low) at 3.9 min, against gpt-oss-120b (High) at 7.5 min for gpt-oss-120b.
For cost per task, gpt-oss-120b is cheapest: gpt-oss-120b (High) at $0.35, against GPT-6 Astra (Low) at $1.42 for GPT-6 Astra.

Model Playground

Releases compared


	GPT-6 Astra (max)	GPT-6 Astra (xhigh)	GPT-6 Astra (high)	GPT-6 Astra (medium)	GPT-6 Astra (low)	gpt-oss-120b (high)	gpt-oss-120b (low)
Intelligence Index	57	55	55	52	43	4	--
Finance & Accounting	57	57	56	54	48	8	--
Strategy & Ops	58	58	57	56	50	6	--
Legal	56	56	55	52	48	8	--
Healthcare & Medical	54	53	52	50	45	6	--
Engineering	62	60	60	57	50	11	--
Economics	57	57	56	53	47	9	--
AA-Briefcase v1.1	1569	1543	1503	1462	1256	0	--
AutomationBench-AA	68.5%	67.2%	66.6%	64.6%	59.1%	0.2%	--
Terminal-Bench 4.0	59.1%	59.6%	54.0%	49.5%	41.9%	0.0%	--
FrontierCode-AA 2.0	42.4%	41.4%	40.1%	36.6%	26.2%	0.0%	--
AA-Omniscience v1.1	42	44	45	41	40	−46	--
GDP.pdf	31.0%	32.2%	31.0%	30.4%	30.4%	4.2%	--
HLE-Diamond	63.8%	61.5%	59.3%	52.7%	45.1%	3.8%	--
CritPt v2 (Hard Subset)	70.5%	71.0%	71.5%	72.0%	63.0%	4.0%	--
Terminal-Bench-Science 0.1	63.3%	54.8%	59.5%	53.3%	37.1%	0.0%	--

Cost per TaskUSD	$6.24	$3.66	$3.24	$2.73	$1.42	$0.35	--
Input PriceUSD/1M Tokens	$10.00	$10.00	$10.00	$10.00	$10.00	$0.15	$0.13
Output PriceUSD/1M Tokens	$50.00	$50.00	$50.00	$50.00	$50.00	$0.60	$0.59
Cache Hit PriceUSD/1M Tokens	$1.00	$1.00	$1.00	$1.00	$1.00	$0.13	$0.13
Cache Write PriceUSD/1M Tokens	$12.50	$12.50	$12.50	$12.50	$12.50	--	--

Time per TaskMinutes	24.1	12.1	9.5	7.7	3.9	7.5	--
Output Speedtok/s	36	37	41	39	39	164	167
Time to First Answer Tokens	253.50	114.55	65.23	7.29	3.88	15.05	2.21
Time to First Tokens	253.50	114.55	65.23	7.29	3.88	1.24	1.23
End-to-End TimeMean of Single-Request Workloads (s)	593.16	341.99	242.09	146.49	114.25	31.78	14.71

Context Window	1M	1M	1M	1M	1M	131k	131k
Creator	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI	OpenAI
License	Proprietary	Proprietary	Proprietary	Proprietary	Proprietary	Open	Open
Input Modality	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text and image	Supports: text	Supports: text
Output Modality	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text	Supports: text
Providers						+12	+11

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Time per Task

Inference time (minutes) per Intelligence Index task · Lower 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 v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 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 Astra

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

Performance

Time per Intelligence Index Task

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

The weighted average time (minutes) per Artificial Analysis Intelligence Index task: output tokens per task divided by output speed, weighted by each benchmark's weight in the Intelligence Index.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

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-AA 2.0, AA-Briefcase v1.1 · Higher is better

Economics Index

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

Benchmarks

AA-PersonalityBenchNew

Personality Indexes

Each axis is one of 8 personality indexes: the mean of its traits’ Elo z-scores, percentile ranked from 1 to 100 across all models evaluated in the benchmark

GPT-6 Astra vs gpt-oss-120b: Release Comparison

Intelligence

Time per Task

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

Performance

Time per Intelligence Index Task

Time per Intelligence Index Task

Time Period

Capability Scores

Capability Indexes

Benchmarks

AA-PersonalityBenchNew

Personality Indexes