Gemini 4 Hydrogen vs Claude Sonnet 5.5: Release Comparison

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

Comparison of the Gemini 4 Hydrogen and Claude Sonnet 5.5 releases: 4 and 5 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 9 models.

For intelligence, Claude Sonnet 5.5 scores highest: Claude Sonnet 5.5 (Max, Default Fallback) at 55, against Gemini 4 Hydrogen (Xhigh) at 54 for Gemini 4 Hydrogen.
For time per task, Gemini 4 Hydrogen is fastest: Gemini 4 Hydrogen (Low) at 1.3 min, against Claude Sonnet 5.5 (Low, Default Fallback) at 2.5 min for Claude Sonnet 5.5.
For cost per task, Gemini 4 Hydrogen is cheapest: Gemini 4 Hydrogen (Low) at $0.29, against Claude Sonnet 5.5 (Low, Default Fallback) at $0.51 for Claude Sonnet 5.5.

Model Playground

Releases compared


	Claude Sonnet 5.5 (max)	Gemini 4 Hydrogen (xhigh)	Gemini 4 Hydrogen (high)	Claude Sonnet 5.5 (xhigh)	Claude Sonnet 5.5 (high)	Gemini 4 Hydrogen (medium)	Claude Sonnet 5.5 (medium)	Gemini 4 Hydrogen (low)	Claude Sonnet 5.5 (low)
Intelligence Index	55	54	51	50	42	41	31	27	26
Finance & Accounting	56	58	56	49	44	51	41	41	36
Strategy & Ops	58	58	55	54	51	52	47	42	42
Legal	52	57	55	47	44	51	39	42	37
Healthcare & Medical	54	--	--	47	44	--	40	--	37
Engineering	58	60	57	54	46	49	37	36	33
Economics	54	55	53	48	45	48	39	38	35
AA-Briefcase v1.1	1816	1567	1497	1742	1634	1296	1439	947	1268
AutomationBench-AA	71.8%	76.1%	74.4%	65.5%	59.4%	72.0%	54.9%	60.5%	49.4%
Terminal-Bench 4.0	63.6%	53.5%	54.0%	57.1%	43.9%	29.3%	29.8%	6.6%	20.7%
FrontierCode-AA 2.0	41.7%	39.0%	36.3%	35.6%	25.7%	31.5%	11.0%	9.3%	7.1%
AA-Omniscience v1.1	30	46	44	21	19	42	19	36	20
GDP.pdf	25.8%	27.6%	30.0%	24.6%	25.2%	32.8%	20.2%	28.2%	16.0%
HLE-Diamond	53.3%	58.8%	54.9%	44.1%	33.8%	47.7%	23.8%	32.2%	20.6%
CritPt v2 (Hard Subset)	59.0%	66.0%	61.5%	57.5%	51.5%	61.0%	33.5%	48.0%	26.0%
Terminal-Bench-Science 0.1	53.3%	49.5%	41.4%	52.4%	34.3%	15.2%	16.2%	2.4%	10.5%

Cost per TaskUSD	$10.02	$3.16	$1.87	$4.09	$1.64	$0.80	$0.78	$0.29	$0.51
Input PriceUSD/1M Tokens	$2.00	$1.50	$1.50	$2.00	$2.00	$1.50	$2.00	$1.50	$2.00
Output PriceUSD/1M Tokens	$10.00	$7.50	$7.50	$10.00	$10.00	$7.50	$10.00	$7.50	$10.00
Cache Hit PriceUSD/1M Tokens	$0.10	$0.075	$0.075	$0.10	$0.10	$0.075	$0.10	$0.075	$0.10
Cache Write PriceUSD/1M Tokens	$2.50	--	--	$2.50	$2.50	--	$2.50	--	$2.50

Time per TaskMinutes	33.0	13.5	8.3	14.6	7.0	3.7	3.8	1.3	2.5
Output Speedtok/s	144	190	170	139	139	177	135	181	137
Time to First Answer Tokens	259.06	37.77	18.89	28.33	10.56	11.80	4.69	5.71	2.73
Time to First Tokens	259.06	37.77	18.89	28.33	10.56	11.80	4.69	5.71	2.73
End-to-End TimeMean of Single-Request Workloads (s)	516.62	96.34	68.50	83.10	47.62	27.44	32.73	19.34	25.52

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

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

Gemini 4 Hydrogen

Claude Sonnet 5.5

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

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

Gemini 4 Hydrogen vs Claude Sonnet 5.5: 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

Speed & Latency

Time per Intelligence Index Task

Time per Intelligence Index Task

Time Period

Capability Scores

Capability Indexes

Benchmarks

AA-PersonalityBenchNew

Personality Indexes