69 models

Google Models: Intelligence, Performance & Price

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

Google

Intelligence

Updated

Gemini 4 Carbon (high)

Gemini 4 Carbon (medium)

Gemini 4 Carbon (low)

Gemini 4 Argon (high)

Gemini 3.8 Flash (high)

Artificial Analysis Intelligence Index

Time per Task

Gemini 3.5 Flash-Lite

1.7 min

Gemini 3.8 Flash (medium)

12.2 min

Gemini 3.8 Flash (high)

14.7 min

Gemini 4 Carbon (low)

23.2 min

Gemini 4 Carbon (medium)

24.4 min

Per Intelligence Index Task

Cost

Gemini 3.5 Flash-Lite

$0.69

Gemini 3.8 Flash (medium)

$6.26

Gemini 4 Carbon (medium)

$6.59

Gemini 4 Carbon (low)

$7.19

Gemini 4 Carbon (high)

$7.76

Per Intelligence Index Task

Artificial Analysis has benchmarked 69 models from Google. Below is a comparison of the key metrics across these models.

For intelligence, the top model from Google is Gemini 4 Carbon (High) at 60.
For speed, Gemini 3.5 Flash-Lite at 1.7 min has the lowest time per task.
For latency, Gemma 4 26B A4B (Non-reasoning) at 1.55s offers the lowest time to first answer token.
For pricing, Gemini 3.5 Flash-Lite at $0.69 offers the lowest cost per task. Prices vary up to 14x across models.

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 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

No publicly available API

Artificial Analysis Intelligence Index v5.0.1 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

Pareto line

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

No publicly available API

Speed & Latency

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

No publicly available API

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 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

All Google Releases

Further details

								Weights		Provider Benchmarks
Gemini 4 Carbon (High)	Google	60	-	1M	$2.94	28.3	72	Not available		View
Gemini 4 Carbon (Medium)	Google	58	-	1M	$2.94	24.4	70	Not available		View
Gemini 4 Carbon (Low)	Google	54	-	1M	$2.94	23.2	62	Not available		View
Gemini 4 Argon (High)	Google	50	-	1M	$2.94	29.4	66	Not available		View
Gemini 3.8 Flash (High)	Google	31	-	1M	$0.58	14.7	112	Not available		View
Gemini 3.8 Flash (Medium)	Google	30	-	1M	$0.58	12.2	112	Not available		View
Gemini 3.8 Flash (Low)	Google	23	-	1M	$0.58	-	100	Not available		View
Gemini 3.5 Flash-Lite	Google	12	-	1M	$0.33	1.7	292	Not available		View
Gemini 3.1 Flash-Lite	Google	6	-	1M	$0.22	0.8	316	Not available		View
Gemma 4 31B (Reasoning)	Google	4	30.7B	256k	$0.00	-	36	🤗	+8	View
Gemini 3.5 Flash (High)	Google	-	-	1M	$1.31	-	181	Not available		View
Gemma 4 12B (Non-reasoning)	Google	-	12B	262k	$0.12	-	71	🤗		View
Gemini 3.5 Flash (Minimal)	Google	-	-	1M	$1.31	-	165	Not available		View
Gemini 2.0 Flash Thinking Experimental (Jan '25)	Google	-	-	1M	-	-	-	Not available	-	View
Gemma 3 270M	Google	-	0.3B	32k	-	-	-	🤗	-	View
Gemini 2.5 Pro Preview (May' 25)	Google	-	-	1M	$1.34	-	-	Not available		View
Gemini 1.5 Pro (May '24)	Google	-	-	2M	-	-	-	Not available	-	View
Gemini 2.5 Flash-Lite (Non-reasoning)	Google	-	-	1M	$0.067	-	272	Not available		View
Gemini 2.5 Flash (Reasoning)	Google	-	-	1M	$0.33	-	208	Not available		View
Gemma 3 4B Instruct	Google	-	4.3B	128k	$0.00	-	106	🤗		View
Gemini 2.5 Pro	Google	-	-	1M	$1.34	-	118	Not available		View
Gemini 1.5 Pro (Sep '24)	Google	-	-	2M	-	-	-	Not available	-	View
Gemini 1.0 Ultra	Google	-	-	33k	-	-	-	Not available	-	View
Gemma 3 27B Instruct	Google	-	27.4B	128k	$0.00	-	32	🤗	+3	View
Gemma 3 12B Instruct	Google	-	12.2B	128k	$0.00	-	49	🤗		View
Gemini 2.0 Flash-Lite (Preview)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 1.5 Flash (Sep '24)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 3.5 Flash (Medium)	Google	-	-	1M	$1.31	-	164	Not available		View
PALM-2	Google	-	-	8k	-	-	-	Not available	-	View
Gemma 4 E4B (Non-reasoning)	Google	-	8B 4.5B active at inference time	128k	$0.028	-	54	🤗		View
Gemini 2.5 Flash Preview (Non-reasoning)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 2.5 Pro Preview (Mar' 25)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 2.5 Flash Preview (Reasoning)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 2.5 Flash (Non-reasoning)	Google	-	-	1M	$0.33	-	168	Not available		View
Gemma 4 26B A4B (Reasoning)	Google	-	25.2B 3.8B active at inference time	256k	$0.089	-	78	🤗	+4	View
Gemma 4 26B A4B (Non-reasoning)	Google	-	25.2B 3.8B active at inference time	256k	$0.11	-	94	🤗	+5	View
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)	Google	-	-	1M	$0.067	-	-	Not available		View
Gemma 4 E2B (Non-reasoning)	Google	-	5.1B 2.3B active at inference time	128k	-	-	-	🤗	-	View
Gemini 3.6 Flash (High)	Google	-	-	1M	$0.63	-	190	Not available		View
Gemini 3 Flash Preview (Non-reasoning)	Google	-	-	1M	$0.43	-	172	Not available		View
Gemini 2.0 Flash-Lite (Feb '25)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 3 Flash Preview (Reasoning)	Google	-	-	1M	$0.43	-	192	Not available		View
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)	Google	-	-	1M	$0.067	-	-	Not available		View
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 1.0 Pro	Google	-	-	33k	-	-	-	Not available	-	View
Gemini 1.5 Flash-8B	Google	-	8B	1M	-	-	-	Not available	-	View
Gemini 3 Deep Think	Google	-	-	128k	-	-	-	Not available	-	View
Gemma 3n E4B Instruct	Google	-	8.4B 4B active at inference time	32k	-	-	-	🤗	-	View
Gemma 3n E2B Instruct	Google	-	6B 2B active at inference time	32k	$0.00	-	-	🤗		View
Gemini 1.5 Flash (May '24)	Google	-	-	1M	-	-	-	Not available	-	View
Gemma 4 E2B (Reasoning)	Google	-	5.1B 2.3B active at inference time	128k	-	-	-	🤗	-	View
Gemini 3.7 Flash (High)	Google	-	-	1M	$0.58	-	-	Not available	-	View
Gemini 3 Pro Preview (Low)	Google	-	-	1M	$1.74	-	-	Not available		View
Gemini 3.1 Pro Preview	Google	-	-	1M	$1.74	-	109	Not available		View
Gemini 2.0 Flash (Feb '25)	Google	-	-	1M	-	-	-	Not available	-	View
Gemma 3n E4B Instruct Preview (May '25)	Google	-	8.4B 4B active at inference time	32k	-	-	-	🤗	-	View
DiffusionGemma 26B A4B	Google	-	25.2B 3.8B active at inference time	256k	-	-	-	🤗	-	View
Gemini 2.0 Pro Experimental (Feb '25)	Google	-	-	2M	-	-	-	Not available	-	View
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)	Google	-	-	1M	-	-	-	Not available	-	View
Gemma 4 31B (Non-reasoning)	Google	-	30.7B	256k	$0.17	-	54	🤗	+7	View
Gemini 3 Pro Preview (High)	Google	-	-	1M	$1.74	-	-	Not available		View
Gemma 3 1B Instruct	Google	-	1B	32k	$0.00	-	-	🤗		View
Gemma 4 E4B (Reasoning)	Google	-	8B 4.5B active at inference time	128k	$0.028	-	56	🤗		View
Gemini 3.7 Flash (Low)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 2.0 Flash Thinking Experimental (Dec '24)	Google	-	-	2M	-	-	-	Not available	-	View
Gemini 3.7 Flash (Medium)	Google	-	-	1M	-	-	-	Not available	-	View
Gemini 2.5 Flash-Lite (Reasoning)	Google	-	-	1M	$0.067	-	364	Not available		View
Gemini 2.0 Flash (experimental)	Google	-	-	1M	$0.00	-	-	Not available		View
Gemma 4 12B (Reasoning)	Google	-	12B	262k	$0.12	-	85	🤗		View

Google Models: Intelligence, Performance & Price

Intelligence

Time per Task

Cost

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

Time per Intelligence Index Task

Time per Intelligence Index Task

Time Period

Capability Scores

Capability Indexes

All Google Releases

Further details